Hugging Face's logo

Almancy
/
practica_3_model

Question Answering
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
 Metrics Community
Almancy commited on
Commit
5791dc9
路
verified 路
1 Parent(s): 1a1a888

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -10
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.6976
20
- - Start Accuracy: 0.3233
21
- - End Accuracy: 0.3467
22
- - Total Accuracy: 0.3350
23
 
24
  ## Model description
25
 
@@ -44,17 +44,16 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 5
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Start Accuracy | End Accuracy | Total Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:------------:|:--------------:|
53
- | 3.6709 | 1.0 | 88 | 3.5084 | 0.105 | 0.1233 | 0.1142 |
54
- | 3.2985 | 2.0 | 176 | 3.1792 | 0.1517 | 0.1917 | 0.1717 |
55
- | 2.7692 | 3.0 | 264 | 2.9276 | 0.2233 | 0.2717 | 0.2475 |
56
- | 2.0799 | 4.0 | 352 | 2.7302 | 0.2967 | 0.3317 | 0.3142 |
57
- | 1.9322 | 5.0 | 440 | 2.6976 | 0.3233 | 0.3467 | 0.3350 |
58
 
59
 
60
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.6045
20
+ - Start Accuracy: 0.3583
21
+ - End Accuracy: 0.3617
22
+ - Total Accuracy: 0.36
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 4
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Start Accuracy | End Accuracy | Total Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:------------:|:--------------:|
53
+ | 3.9153 | 1.0 | 88 | 3.5519 | 0.115 | 0.1483 | 0.1317 |
54
+ | 3.0556 | 2.0 | 176 | 3.0543 | 0.225 | 0.2367 | 0.2308 |
55
+ | 2.2324 | 3.0 | 264 | 2.6733 | 0.3317 | 0.3467 | 0.3392 |
56
+ | 1.939 | 4.0 | 352 | 2.6045 | 0.3583 | 0.3617 | 0.36 |
 
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae5c5f85b4145e40744fed04ebb103cac5271f893b4704c34beba563d938b82f
3
  size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b9c4d0ad3dd0698d40d48d45248ff72c069307ae87fe8c944df6a89ec745f1
3
  size 265470032
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3623df77edb38d2ba2be372028b2e344f8415dec216bfe0df37842b170dbc32
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61f6929c3c32e76bf90df98e7b3723d8aaef7987a63d5730f2aee5537ec384aa
3
  size 5176