Commit
•
4746847
1
Parent(s):
e1f69b7
End of training
Browse files- README.md +111 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: distilgpt2
|
7 |
+
model-index:
|
8 |
+
- name: distilgpt-monolinugal
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# distilgpt-monolinugal
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 3.4876
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0005
|
39 |
+
- train_batch_size: 12
|
40 |
+
- eval_batch_size: 12
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 8
|
43 |
+
- total_train_batch_size: 96
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- lr_scheduler_warmup_steps: 100
|
47 |
+
- num_epochs: 8
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 3.3098 | 0.16 | 200 | 3.5905 |
|
55 |
+
| 3.2847 | 0.32 | 400 | 3.5644 |
|
56 |
+
| 3.2612 | 0.48 | 600 | 3.5504 |
|
57 |
+
| 3.2636 | 0.64 | 800 | 3.5384 |
|
58 |
+
| 3.2481 | 0.8 | 1000 | 3.5301 |
|
59 |
+
| 3.2393 | 0.96 | 1200 | 3.5233 |
|
60 |
+
| 3.2381 | 1.12 | 1400 | 3.5184 |
|
61 |
+
| 3.2317 | 1.28 | 1600 | 3.5168 |
|
62 |
+
| 3.2244 | 1.44 | 1800 | 3.5123 |
|
63 |
+
| 3.2258 | 1.6 | 2000 | 3.5117 |
|
64 |
+
| 3.2238 | 1.76 | 2200 | 3.5058 |
|
65 |
+
| 3.2376 | 1.92 | 2400 | 3.5058 |
|
66 |
+
| 3.212 | 2.08 | 2600 | 3.5044 |
|
67 |
+
| 3.231 | 2.24 | 2800 | 3.5019 |
|
68 |
+
| 3.2044 | 2.4 | 3000 | 3.5003 |
|
69 |
+
| 3.2107 | 2.57 | 3200 | 3.5002 |
|
70 |
+
| 3.2096 | 2.73 | 3400 | 3.4996 |
|
71 |
+
| 3.215 | 2.89 | 3600 | 3.4963 |
|
72 |
+
| 3.2092 | 3.05 | 3800 | 3.4979 |
|
73 |
+
| 3.2034 | 3.21 | 4000 | 3.4964 |
|
74 |
+
| 3.1992 | 3.37 | 4200 | 3.4971 |
|
75 |
+
| 3.1975 | 3.53 | 4400 | 3.4941 |
|
76 |
+
| 3.222 | 3.69 | 4600 | 3.4932 |
|
77 |
+
| 3.2104 | 3.85 | 4800 | 3.4927 |
|
78 |
+
| 3.199 | 4.01 | 5000 | 3.4918 |
|
79 |
+
| 3.2033 | 4.17 | 5200 | 3.4927 |
|
80 |
+
| 3.201 | 4.33 | 5400 | 3.4924 |
|
81 |
+
| 3.1947 | 4.49 | 5600 | 3.4931 |
|
82 |
+
| 3.2172 | 4.65 | 5800 | 3.4907 |
|
83 |
+
| 3.201 | 4.81 | 6000 | 3.4908 |
|
84 |
+
| 3.2089 | 4.97 | 6200 | 3.4892 |
|
85 |
+
| 3.206 | 5.13 | 6400 | 3.4896 |
|
86 |
+
| 3.2074 | 5.29 | 6600 | 3.4884 |
|
87 |
+
| 3.2046 | 5.45 | 6800 | 3.4891 |
|
88 |
+
| 3.1899 | 5.61 | 7000 | 3.4888 |
|
89 |
+
| 3.196 | 5.77 | 7200 | 3.4891 |
|
90 |
+
| 3.1946 | 5.93 | 7400 | 3.4880 |
|
91 |
+
| 3.1951 | 6.09 | 7600 | 3.4887 |
|
92 |
+
| 3.1998 | 6.25 | 7800 | 3.4878 |
|
93 |
+
| 3.1775 | 6.41 | 8000 | 3.4880 |
|
94 |
+
| 3.1947 | 6.57 | 8200 | 3.4880 |
|
95 |
+
| 3.1876 | 6.73 | 8400 | 3.4876 |
|
96 |
+
| 3.1984 | 6.89 | 8600 | 3.4878 |
|
97 |
+
| 3.1927 | 7.05 | 8800 | 3.4875 |
|
98 |
+
| 3.2006 | 7.21 | 9000 | 3.4875 |
|
99 |
+
| 3.2042 | 7.37 | 9200 | 3.4875 |
|
100 |
+
| 3.1856 | 7.54 | 9400 | 3.4877 |
|
101 |
+
| 3.1952 | 7.7 | 9600 | 3.4877 |
|
102 |
+
| 3.1981 | 7.86 | 9800 | 3.4876 |
|
103 |
+
|
104 |
+
|
105 |
+
### Framework versions
|
106 |
+
|
107 |
+
- PEFT 0.7.1
|
108 |
+
- Transformers 4.36.2
|
109 |
+
- Pytorch 1.13.0+cu116
|
110 |
+
- Datasets 2.16.0
|
111 |
+
- Tokenizers 0.15.0
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 315310960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81d20fcce92c0be5e8d3b391bb75587cb9f2f54a05ab5a65c618dcbca081b450
|
3 |
size 315310960
|