kearney commited on
Commit
1332ff6
1 Parent(s): cff098d

End of training

Browse files
Files changed (3) hide show
  1. README.md +36 -19
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.3478
21
- - Accuracy: 0.3247
22
 
23
  ## Model description
24
 
@@ -38,7 +38,7 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 3.3e-06
41
- - train_batch_size: 8
42
  - eval_batch_size: 4
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -49,22 +49,39 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | 2.4973 | 0.18 | 200 | 2.4079 | 0.3173 |
53
- | 2.4484 | 0.36 | 400 | 2.4126 | 0.3077 |
54
- | 2.398 | 0.54 | 600 | 2.3910 | 0.314 |
55
- | 2.4151 | 0.72 | 800 | 2.3812 | 0.317 |
56
- | 2.3982 | 0.9 | 1000 | 2.3672 | 0.327 |
57
- | 2.3402 | 1.08 | 1200 | 2.3622 | 0.3263 |
58
- | 2.3362 | 1.26 | 1400 | 2.3591 | 0.3253 |
59
- | 2.3865 | 1.43 | 1600 | 2.3641 | 0.3177 |
60
- | 2.3623 | 1.61 | 1800 | 2.3553 | 0.3253 |
61
- | 2.3528 | 1.79 | 2000 | 2.3576 | 0.3213 |
62
- | 2.3225 | 1.97 | 2200 | 2.3488 | 0.3257 |
63
- | 2.342 | 2.15 | 2400 | 2.3486 | 0.326 |
64
- | 2.3279 | 2.33 | 2600 | 2.3588 | 0.3197 |
65
- | 2.3177 | 2.51 | 2800 | 2.3472 | 0.3217 |
66
- | 2.3509 | 2.69 | 3000 | 2.3483 | 0.3273 |
67
- | 2.325 | 2.87 | 3200 | 2.3478 | 0.3247 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.3380
21
+ - Accuracy: 0.3293
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 3.3e-06
41
+ - train_batch_size: 4
42
  - eval_batch_size: 4
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 2.2896 | 0.09 | 200 | 2.3458 | 0.328 |
53
+ | 2.3881 | 0.18 | 400 | 2.3456 | 0.3207 |
54
+ | 2.3149 | 0.27 | 600 | 2.3552 | 0.3283 |
55
+ | 2.2579 | 0.36 | 800 | 2.3468 | 0.327 |
56
+ | 2.3016 | 0.45 | 1000 | 2.3512 | 0.327 |
57
+ | 2.3923 | 0.54 | 1200 | 2.3410 | 0.3313 |
58
+ | 2.3458 | 0.63 | 1400 | 2.3416 | 0.328 |
59
+ | 2.3522 | 0.72 | 1600 | 2.3303 | 0.3287 |
60
+ | 2.2485 | 0.81 | 1800 | 2.3291 | 0.3343 |
61
+ | 2.3083 | 0.9 | 2000 | 2.3289 | 0.3327 |
62
+ | 2.2594 | 0.99 | 2200 | 2.3336 | 0.3387 |
63
+ | 2.229 | 1.08 | 2400 | 2.3446 | 0.3213 |
64
+ | 2.3017 | 1.17 | 2600 | 2.3362 | 0.3327 |
65
+ | 2.2405 | 1.26 | 2800 | 2.3299 | 0.335 |
66
+ | 2.3291 | 1.35 | 3000 | 2.3291 | 0.33 |
67
+ | 2.2518 | 1.43 | 3200 | 2.3363 | 0.3297 |
68
+ | 2.268 | 1.52 | 3400 | 2.3623 | 0.3187 |
69
+ | 2.3198 | 1.61 | 3600 | 2.3480 | 0.3277 |
70
+ | 2.1873 | 1.7 | 3800 | 2.3355 | 0.3293 |
71
+ | 2.2634 | 1.79 | 4000 | 2.3291 | 0.326 |
72
+ | 2.1011 | 1.88 | 4200 | 2.3345 | 0.333 |
73
+ | 2.1965 | 1.97 | 4400 | 2.3383 | 0.3293 |
74
+ | 2.2368 | 2.06 | 4600 | 2.3320 | 0.329 |
75
+ | 2.2226 | 2.15 | 4800 | 2.3453 | 0.3263 |
76
+ | 2.2354 | 2.24 | 5000 | 2.3372 | 0.33 |
77
+ | 2.2829 | 2.33 | 5200 | 2.3547 | 0.3223 |
78
+ | 2.1544 | 2.42 | 5400 | 2.3336 | 0.3287 |
79
+ | 2.2777 | 2.51 | 5600 | 2.3425 | 0.3283 |
80
+ | 2.0763 | 2.6 | 5800 | 2.3339 | 0.3307 |
81
+ | 2.2738 | 2.69 | 6000 | 2.3389 | 0.3293 |
82
+ | 2.1013 | 2.78 | 6200 | 2.3411 | 0.327 |
83
+ | 2.1058 | 2.87 | 6400 | 2.3357 | 0.332 |
84
+ | 2.1621 | 2.96 | 6600 | 2.3380 | 0.3293 |
85
 
86
 
87
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9ac29c3b4fc536a6c43fdaec43408bff3916fc1b75774c1b75ad521d9766ca4
3
  size 267974061
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b97b1c1cc234dc3e7806a83c7d8514b3e38703205a8945e6df8364bef8ac96
3
  size 267974061
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c63d7d33093b4d04a890166adbb5f5a69ae0b400604b2296146171690830ff50
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca52886750a1b05ad2f299bbcecea11da584901c2158abc7f50677a847705e2b
3
  size 4027