bigmorning
commited on
Commit
•
b96270c
1
Parent(s):
4946994
add model
Browse files- README.md +71 -0
- config.json +45 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_keras_callback
|
4 |
+
model-index:
|
5 |
+
- name: distilgpt_new5_0020
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
10 |
+
probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# distilgpt_new5_0020
|
13 |
+
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Train Loss: 2.4736
|
17 |
+
- Validation Loss: 2.3530
|
18 |
+
- Epoch: 19
|
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 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
38 |
+
- training_precision: float32
|
39 |
+
|
40 |
+
### Training results
|
41 |
+
|
42 |
+
| Train Loss | Validation Loss | Epoch |
|
43 |
+
|:----------:|:---------------:|:-----:|
|
44 |
+
| 2.4839 | 2.3639 | 0 |
|
45 |
+
| 2.4833 | 2.3630 | 1 |
|
46 |
+
| 2.4827 | 2.3620 | 2 |
|
47 |
+
| 2.4821 | 2.3632 | 3 |
|
48 |
+
| 2.4816 | 2.3617 | 4 |
|
49 |
+
| 2.4811 | 2.3614 | 5 |
|
50 |
+
| 2.4805 | 2.3613 | 6 |
|
51 |
+
| 2.4799 | 2.3613 | 7 |
|
52 |
+
| 2.4794 | 2.3600 | 8 |
|
53 |
+
| 2.4788 | 2.3589 | 9 |
|
54 |
+
| 2.4784 | 2.3582 | 10 |
|
55 |
+
| 2.4779 | 2.3563 | 11 |
|
56 |
+
| 2.4774 | 2.3579 | 12 |
|
57 |
+
| 2.4768 | 2.3563 | 13 |
|
58 |
+
| 2.4762 | 2.3561 | 14 |
|
59 |
+
| 2.4756 | 2.3554 | 15 |
|
60 |
+
| 2.4751 | 2.3539 | 16 |
|
61 |
+
| 2.4746 | 2.3550 | 17 |
|
62 |
+
| 2.4741 | 2.3534 | 18 |
|
63 |
+
| 2.4736 | 2.3530 | 19 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.20.1
|
69 |
+
- TensorFlow 2.8.2
|
70 |
+
- Datasets 2.4.0
|
71 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/Colab Notebooks/oscar/trybackup/new_backup4_00055",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"transformers_version": "4.20.1",
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 27672
|
45 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:840df181f093836eddfa3a0330bb46389ad0b257ec771573efa73d78551982a4
|
3 |
+
size 258364376
|