End of training
Browse files- README.md +111 -0
- adapter_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: camembert/camembert-base-ccnet
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: camembert_ccnet_classification_tools_qlora_fr
|
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 |
+
# camembert_ccnet_classification_tools_qlora_fr
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [camembert/camembert-base-ccnet](https://huggingface.co/camembert/camembert-base-ccnet) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.4958
|
20 |
+
- Accuracy: 0.45
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0001
|
40 |
+
- train_batch_size: 24
|
41 |
+
- eval_batch_size: 192
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 60
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
51 |
+
| No log | 1.0 | 5 | 2.0916 | 0.075 |
|
52 |
+
| No log | 2.0 | 10 | 2.1165 | 0.075 |
|
53 |
+
| No log | 3.0 | 15 | 2.1285 | 0.075 |
|
54 |
+
| No log | 4.0 | 20 | 2.1210 | 0.075 |
|
55 |
+
| No log | 5.0 | 25 | 2.1182 | 0.125 |
|
56 |
+
| No log | 6.0 | 30 | 2.0984 | 0.125 |
|
57 |
+
| No log | 7.0 | 35 | 2.0764 | 0.15 |
|
58 |
+
| No log | 8.0 | 40 | 2.0390 | 0.2 |
|
59 |
+
| No log | 9.0 | 45 | 2.0085 | 0.2 |
|
60 |
+
| No log | 10.0 | 50 | 1.9749 | 0.175 |
|
61 |
+
| No log | 11.0 | 55 | 1.9474 | 0.15 |
|
62 |
+
| No log | 12.0 | 60 | 1.9271 | 0.225 |
|
63 |
+
| No log | 13.0 | 65 | 1.9089 | 0.225 |
|
64 |
+
| No log | 14.0 | 70 | 1.8945 | 0.225 |
|
65 |
+
| No log | 15.0 | 75 | 1.8847 | 0.2 |
|
66 |
+
| No log | 16.0 | 80 | 1.8638 | 0.25 |
|
67 |
+
| No log | 17.0 | 85 | 1.8387 | 0.3 |
|
68 |
+
| No log | 18.0 | 90 | 1.8156 | 0.275 |
|
69 |
+
| No log | 19.0 | 95 | 1.8003 | 0.3 |
|
70 |
+
| No log | 20.0 | 100 | 1.7827 | 0.275 |
|
71 |
+
| No log | 21.0 | 105 | 1.7688 | 0.3 |
|
72 |
+
| No log | 22.0 | 110 | 1.7467 | 0.275 |
|
73 |
+
| No log | 23.0 | 115 | 1.7255 | 0.275 |
|
74 |
+
| No log | 24.0 | 120 | 1.7132 | 0.325 |
|
75 |
+
| No log | 25.0 | 125 | 1.7007 | 0.35 |
|
76 |
+
| No log | 26.0 | 130 | 1.6881 | 0.35 |
|
77 |
+
| No log | 27.0 | 135 | 1.6801 | 0.35 |
|
78 |
+
| No log | 28.0 | 140 | 1.6642 | 0.375 |
|
79 |
+
| No log | 29.0 | 145 | 1.6450 | 0.325 |
|
80 |
+
| No log | 30.0 | 150 | 1.6425 | 0.35 |
|
81 |
+
| No log | 31.0 | 155 | 1.6305 | 0.375 |
|
82 |
+
| No log | 32.0 | 160 | 1.6193 | 0.4 |
|
83 |
+
| No log | 33.0 | 165 | 1.6128 | 0.4 |
|
84 |
+
| No log | 34.0 | 170 | 1.6027 | 0.4 |
|
85 |
+
| No log | 35.0 | 175 | 1.5915 | 0.425 |
|
86 |
+
| No log | 36.0 | 180 | 1.5837 | 0.45 |
|
87 |
+
| No log | 37.0 | 185 | 1.5721 | 0.45 |
|
88 |
+
| No log | 38.0 | 190 | 1.5605 | 0.425 |
|
89 |
+
| No log | 39.0 | 195 | 1.5555 | 0.425 |
|
90 |
+
| No log | 40.0 | 200 | 1.5521 | 0.425 |
|
91 |
+
| No log | 41.0 | 205 | 1.5480 | 0.425 |
|
92 |
+
| No log | 42.0 | 210 | 1.5399 | 0.45 |
|
93 |
+
| No log | 43.0 | 215 | 1.5276 | 0.45 |
|
94 |
+
| No log | 44.0 | 220 | 1.5282 | 0.45 |
|
95 |
+
| No log | 45.0 | 225 | 1.5197 | 0.45 |
|
96 |
+
| No log | 46.0 | 230 | 1.5175 | 0.45 |
|
97 |
+
| No log | 47.0 | 235 | 1.5065 | 0.45 |
|
98 |
+
| No log | 48.0 | 240 | 1.5043 | 0.45 |
|
99 |
+
| No log | 49.0 | 245 | 1.5019 | 0.45 |
|
100 |
+
| No log | 50.0 | 250 | 1.4975 | 0.45 |
|
101 |
+
| No log | 51.0 | 255 | 1.4949 | 0.45 |
|
102 |
+
| No log | 52.0 | 260 | 1.4969 | 0.45 |
|
103 |
+
| No log | 53.0 | 265 | 1.4958 | 0.45 |
|
104 |
+
|
105 |
+
|
106 |
+
### Framework versions
|
107 |
+
|
108 |
+
- Transformers 4.34.0
|
109 |
+
- Pytorch 2.0.1+cu117
|
110 |
+
- Datasets 2.14.5
|
111 |
+
- Tokenizers 0.14.1
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7571689
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7a3528255f6694734ef130dedaf9f8efcb9bc29d22cefac01f8d47a85a738eb
|
3 |
size 7571689
|