Commit
•
b00a02a
1
Parent(s):
7e7eed6
add model
Browse files- README.md +86 -0
- config.json +45 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_keras_callback
|
4 |
+
model-index:
|
5 |
+
- name: distilgpt_new3_0035
|
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_new3_0035
|
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: 2.5161
|
17 |
+
- Validation Loss: 2.3990
|
18 |
+
- Epoch: 34
|
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 |
+
| 2.5407 | 2.4254 | 0 |
|
45 |
+
| 2.5399 | 2.4247 | 1 |
|
46 |
+
| 2.5391 | 2.4238 | 2 |
|
47 |
+
| 2.5383 | 2.4232 | 3 |
|
48 |
+
| 2.5375 | 2.4210 | 4 |
|
49 |
+
| 2.5368 | 2.4210 | 5 |
|
50 |
+
| 2.5361 | 2.4197 | 6 |
|
51 |
+
| 2.5353 | 2.4193 | 7 |
|
52 |
+
| 2.5345 | 2.4191 | 8 |
|
53 |
+
| 2.5339 | 2.4177 | 9 |
|
54 |
+
| 2.5332 | 2.4188 | 10 |
|
55 |
+
| 2.5324 | 2.4160 | 11 |
|
56 |
+
| 2.5317 | 2.4164 | 12 |
|
57 |
+
| 2.5309 | 2.4145 | 13 |
|
58 |
+
| 2.5302 | 2.4153 | 14 |
|
59 |
+
| 2.5295 | 2.4139 | 15 |
|
60 |
+
| 2.5288 | 2.4134 | 16 |
|
61 |
+
| 2.5282 | 2.4123 | 17 |
|
62 |
+
| 2.5274 | 2.4116 | 18 |
|
63 |
+
| 2.5267 | 2.4110 | 19 |
|
64 |
+
| 2.5259 | 2.4106 | 20 |
|
65 |
+
| 2.5251 | 2.4097 | 21 |
|
66 |
+
| 2.5244 | 2.4074 | 22 |
|
67 |
+
| 2.5238 | 2.4078 | 23 |
|
68 |
+
| 2.5232 | 2.4072 | 24 |
|
69 |
+
| 2.5223 | 2.4062 | 25 |
|
70 |
+
| 2.5217 | 2.4054 | 26 |
|
71 |
+
| 2.5211 | 2.4057 | 27 |
|
72 |
+
| 2.5204 | 2.4044 | 28 |
|
73 |
+
| 2.5197 | 2.4026 | 29 |
|
74 |
+
| 2.5189 | 2.4017 | 30 |
|
75 |
+
| 2.5182 | 2.4026 | 31 |
|
76 |
+
| 2.5176 | 2.4012 | 32 |
|
77 |
+
| 2.5168 | 2.4013 | 33 |
|
78 |
+
| 2.5161 | 2.3990 | 34 |
|
79 |
+
|
80 |
+
|
81 |
+
### Framework versions
|
82 |
+
|
83 |
+
- Transformers 4.20.1
|
84 |
+
- TensorFlow 2.8.2
|
85 |
+
- Datasets 2.3.2
|
86 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/Colab Notebooks/oscar/trybackup/new_backup2_008585",
|
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 sha256:22757a7645d3760428d0d3d684e2ebd2c987cc34023ceea6e44d1ef229cee94a
|
3 |
+
size 258364376
|