Hugging Face's logo

Rzoro
/
checkpoints_1_18

Multiple Choice
Transformers
PyTorch
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
Rzoro commited on
Commit
3f35240
•
1 Parent(s): 6908543

Model save

Browse files
Files changed (1) hide show
  1. README.md +15 -36
README.md CHANGED
@@ -1,6 +1,4 @@
1
  ---
2
- license: mit
3
- base_model: microsoft/deberta-v3-large
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,10 +11,10 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # checkpoints_1_18
15
 
16
- This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.0089
19
- - Map@3: 0.7285
20
 
21
  ## Model description
22
 
@@ -44,40 +42,21 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.1
47
- - num_epochs: 3
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Map@3 |
52
- |:-------------:|:-----:|:-----:|:---------------:|:------:|
53
- | 1.6121 | 0.11 | 500 | 1.5976 | 0.6680 |
54
- | 1.4289 | 0.21 | 1000 | 1.1233 | 0.7035 |
55
- | 1.3446 | 0.32 | 1500 | 1.0928 | 0.7092 |
56
- | 1.3192 | 0.42 | 2000 | 1.0716 | 0.7087 |
57
- | 1.2756 | 0.53 | 2500 | 1.0657 | 0.7067 |
58
- | 1.2689 | 0.63 | 3000 | 1.0685 | 0.7193 |
59
- | 1.2736 | 0.74 | 3500 | 1.0163 | 0.7083 |
60
- | 1.2339 | 0.84 | 4000 | 1.0123 | 0.7182 |
61
- | 1.2439 | 0.95 | 4500 | 1.0174 | 0.7233 |
62
- | 1.2303 | 1.05 | 5000 | 1.0037 | 0.7197 |
63
- | 1.2128 | 1.16 | 5500 | 1.0335 | 0.7263 |
64
- | 1.2259 | 1.26 | 6000 | 1.0124 | 0.7190 |
65
- | 1.21 | 1.37 | 6500 | 1.0217 | 0.7227 |
66
- | 1.1958 | 1.47 | 7000 | 1.0010 | 0.7292 |
67
- | 1.1967 | 1.58 | 7500 | 1.0042 | 0.7245 |
68
- | 1.1831 | 1.68 | 8000 | 1.0252 | 0.7317 |
69
- | 1.2083 | 1.79 | 8500 | 1.0379 | 0.7387 |
70
- | 1.1986 | 1.9 | 9000 | 1.0299 | 0.7292 |
71
- | 1.1866 | 2.0 | 9500 | 1.0024 | 0.7308 |
72
- | 1.1635 | 2.11 | 10000 | 1.0086 | 0.7290 |
73
- | 1.1575 | 2.21 | 10500 | 1.0042 | 0.7252 |
74
- | 1.1674 | 2.32 | 11000 | 1.0056 | 0.7283 |
75
- | 1.1572 | 2.42 | 11500 | 1.0119 | 0.7260 |
76
- | 1.1498 | 2.53 | 12000 | 1.0074 | 0.7250 |
77
- | 1.1489 | 2.63 | 12500 | 1.0054 | 0.7277 |
78
- | 1.1478 | 2.74 | 13000 | 1.0094 | 0.7278 |
79
- | 1.165 | 2.84 | 13500 | 1.0080 | 0.7282 |
80
- | 1.1265 | 2.95 | 14000 | 1.0089 | 0.7285 |
81
 
82
 
83
  ### Framework versions
 
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
  model-index:
 
11
 
12
  # checkpoints_1_18
13
 
14
+ This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 1.0012
17
+ - Map@3: 0.7287
18
 
19
  ## Model description
20
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.1
45
+ - num_epochs: 1
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | Map@3 |
50
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
51
+ | 1.2427 | 0.11 | 500 | 1.0237 | 0.7212 |
52
+ | 1.2405 | 0.21 | 1000 | 1.0134 | 0.7207 |
53
+ | 1.2422 | 0.32 | 1500 | 1.0270 | 0.7100 |
54
+ | 1.2396 | 0.42 | 2000 | 1.0296 | 0.7190 |
55
+ | 1.2227 | 0.53 | 2500 | 1.0178 | 0.7227 |
56
+ | 1.2034 | 0.63 | 3000 | 1.0097 | 0.7202 |
57
+ | 1.2138 | 0.74 | 3500 | 1.0076 | 0.7267 |
58
+ | 1.2082 | 0.84 | 4000 | 1.0036 | 0.7278 |
59
+ | 1.2161 | 0.95 | 4500 | 1.0012 | 0.7287 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions