Samuael commited on
Commit
f89f756
·
verified ·
1 Parent(s): 70dd14a

Samuael/amBART_1000

Browse files
Files changed (3) hide show
  1. README.md +2 -67
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -2,9 +2,6 @@
2
  base_model: Samuael/amBART_1000
3
  tags:
4
  - generated_from_trainer
5
- metrics:
6
- - wer
7
- - bleu
8
  model-index:
9
  - name: amBART_1000
10
  results: []
@@ -16,12 +13,6 @@ should probably proofread and complete it, then remove this comment. -->
16
  # amBART_1000
17
 
18
  This model is a fine-tuned version of [Samuael/amBART_1000](https://huggingface.co/Samuael/amBART_1000) on an unknown dataset.
19
- It achieves the following results on the evaluation set:
20
- - Loss: 5.9045
21
- - Wer: 1.0
22
- - Cer: 0.9495
23
- - Bleu: 0.0
24
- - Lr: 0.002
25
 
26
  ## Model description
27
 
@@ -40,69 +31,13 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 0.002
44
  - train_batch_size: 256
45
  - eval_batch_size: 256
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 50
50
-
51
- ### Training results
52
-
53
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Bleu | Lr |
54
- |:-------------:|:-----:|:-----:|:---------------:|:---:|:------:|:----:|:-----:|
55
- | 5.9705 | 1.0 | 355 | 5.9604 | 1.0 | 0.9493 | 0.0 | 0.002 |
56
- | 5.9676 | 2.0 | 710 | 5.9745 | 1.0 | 0.9931 | 0.0 | 0.002 |
57
- | 5.9393 | 3.0 | 1065 | 6.0382 | 1.0 | 5.0803 | 0.0 | 0.002 |
58
- | 5.9333 | 4.0 | 1420 | 5.9475 | 1.0 | 0.9820 | 0.0 | 0.002 |
59
- | 5.9306 | 5.0 | 1775 | 5.9335 | 1.0 | 0.9482 | 0.0 | 0.002 |
60
- | 5.9325 | 6.0 | 2130 | 5.9373 | 1.0 | 0.9481 | 0.0 | 0.002 |
61
- | 5.9357 | 7.0 | 2485 | 5.9318 | 1.0 | 0.9455 | 0.0 | 0.002 |
62
- | 5.9322 | 8.0 | 2840 | 5.9258 | 1.0 | 0.9489 | 0.0 | 0.002 |
63
- | 6.0007 | 9.0 | 3195 | 5.9377 | 1.0 | 0.9489 | 0.0 | 0.002 |
64
- | 5.9307 | 10.0 | 3550 | 5.9205 | 1.0 | 0.9492 | 0.0 | 0.002 |
65
- | 6.1062 | 11.0 | 3905 | 6.0221 | 1.0 | 1.8150 | 0.0 | 0.002 |
66
- | 5.9387 | 12.0 | 4260 | 5.9210 | 1.0 | 0.9456 | 0.0 | 0.002 |
67
- | 5.92 | 13.0 | 4615 | 5.9182 | 1.0 | 0.9488 | 0.0 | 0.002 |
68
- | 5.9279 | 14.0 | 4970 | 5.9472 | 1.0 | 0.9463 | 0.0 | 0.002 |
69
- | 5.918 | 15.0 | 5325 | 5.9202 | 1.0 | 0.9509 | 0.0 | 0.002 |
70
- | 5.9172 | 16.0 | 5680 | 5.9145 | 1.0 | 0.9457 | 0.0 | 0.002 |
71
- | 5.9152 | 17.0 | 6035 | 5.9182 | 1.0 | 0.9689 | 0.0 | 0.002 |
72
- | 5.9296 | 18.0 | 6390 | 5.9260 | 1.0 | 0.9631 | 0.0 | 0.002 |
73
- | 5.9299 | 19.0 | 6745 | 5.9467 | 1.0 | 0.9479 | 0.0 | 0.002 |
74
- | 5.9271 | 20.0 | 7100 | 5.9229 | 1.0 | 0.9474 | 0.0 | 0.002 |
75
- | 5.9303 | 21.0 | 7455 | 5.9263 | 1.0 | 0.9458 | 0.0 | 0.002 |
76
- | 5.9337 | 22.0 | 7810 | 5.9329 | 1.0 | 0.9469 | 0.0 | 0.002 |
77
- | 5.9339 | 23.0 | 8165 | 5.9282 | 1.0 | 0.9559 | 0.0 | 0.002 |
78
- | 5.927 | 24.0 | 8520 | 5.9249 | 1.0 | 0.9502 | 0.0 | 0.002 |
79
- | 5.9256 | 25.0 | 8875 | 5.9251 | 1.0 | 0.9528 | 0.0 | 0.002 |
80
- | 5.9262 | 26.0 | 9230 | 5.9291 | 1.0 | 0.9642 | 0.0 | 0.002 |
81
- | 5.9234 | 27.0 | 9585 | 5.9202 | 1.0 | 0.9468 | 0.0 | 0.002 |
82
- | 5.9298 | 28.0 | 9940 | 5.9254 | 1.0 | 0.9511 | 0.0 | 0.002 |
83
- | 5.9247 | 29.0 | 10295 | 5.9160 | 1.0 | 0.9476 | 0.0 | 0.002 |
84
- | 5.9283 | 30.0 | 10650 | 5.9233 | 1.0 | 0.9550 | 0.0 | 0.002 |
85
- | 5.9286 | 31.0 | 11005 | 5.9173 | 1.0 | 0.9548 | 0.0 | 0.002 |
86
- | 5.9182 | 32.0 | 11360 | 5.9135 | 1.0 | 0.9542 | 0.0 | 0.002 |
87
- | 5.9136 | 33.0 | 11715 | 5.9101 | 1.0 | 0.9532 | 0.0 | 0.002 |
88
- | 5.9128 | 34.0 | 12070 | 5.9138 | 1.0 | 0.9536 | 0.0 | 0.002 |
89
- | 5.9156 | 35.0 | 12425 | 5.9117 | 1.0 | 0.9517 | 0.0 | 0.002 |
90
- | 5.9173 | 36.0 | 12780 | 5.9085 | 1.0 | 0.9508 | 0.0 | 0.002 |
91
- | 5.9121 | 37.0 | 13135 | 5.9086 | 1.0 | 0.9529 | 0.0 | 0.002 |
92
- | 5.9101 | 38.0 | 13490 | 5.9095 | 1.0 | 0.9630 | 0.0 | 0.002 |
93
- | 5.9123 | 39.0 | 13845 | 5.9076 | 1.0 | 0.9515 | 0.0 | 0.002 |
94
- | 5.9127 | 40.0 | 14200 | 5.9082 | 1.0 | 0.9540 | 0.0 | 0.002 |
95
- | 5.9148 | 41.0 | 14555 | 5.9080 | 1.0 | 0.9518 | 0.0 | 0.002 |
96
- | 5.9136 | 42.0 | 14910 | 5.9073 | 1.0 | 0.9488 | 0.0 | 0.002 |
97
- | 5.9097 | 43.0 | 15265 | 5.9070 | 1.0 | 0.9487 | 0.0 | 0.002 |
98
- | 5.9117 | 44.0 | 15620 | 5.9066 | 1.0 | 0.9504 | 0.0 | 0.002 |
99
- | 5.9115 | 45.0 | 15975 | 5.9080 | 1.0 | 0.9477 | 0.0 | 0.002 |
100
- | 5.9104 | 46.0 | 16330 | 5.9064 | 1.0 | 0.9487 | 0.0 | 0.002 |
101
- | 5.9114 | 47.0 | 16685 | 5.9044 | 1.0 | 0.9485 | 0.0 | 0.002 |
102
- | 5.9067 | 48.0 | 17040 | 5.9045 | 1.0 | 0.9488 | 0.0 | 0.002 |
103
- | 5.9085 | 49.0 | 17395 | 5.9047 | 1.0 | 0.9486 | 0.0 | 0.002 |
104
- | 5.9104 | 50.0 | 17750 | 5.9045 | 1.0 | 0.9495 | 0.0 | 0.002 |
105
-
106
 
107
  ### Framework versions
108
 
 
2
  base_model: Samuael/amBART_1000
3
  tags:
4
  - generated_from_trainer
 
 
 
5
  model-index:
6
  - name: amBART_1000
7
  results: []
 
13
  # amBART_1000
14
 
15
  This model is a fine-tuned version of [Samuael/amBART_1000](https://huggingface.co/Samuael/amBART_1000) on an unknown dataset.
 
 
 
 
 
 
16
 
17
  ## Model description
18
 
 
31
  ### Training hyperparameters
32
 
33
  The following hyperparameters were used during training:
34
+ - learning_rate: 0.02
35
  - train_batch_size: 256
36
  - eval_batch_size: 256
37
  - seed: 42
38
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
  - lr_scheduler_type: linear
40
+ - num_epochs: 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
 
42
  ### Framework versions
43
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9e391343f4c512ac2078e3baac43581cc4de5b124e7cb5cdeae176cc054bc14
3
  size 180813204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ee15797df24d6a2296831e704190a0ff42efbf721b3144c70630cbfacbd4de
3
  size 180813204
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9712bce830cd935a0b20fa941916331ae0a1c17b800422168925d7236676a92
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d077861f2d8111c7750d748d173942efb47dfb53e0755cbb758072ce40dc9b
3
  size 4984