Model save
Browse files- README.md +121 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- wer
|
7 |
+
model-index:
|
8 |
+
- name: outputs
|
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 |
+
# outputs
|
16 |
+
|
17 |
+
This model was trained from scratch on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 551.5420
|
20 |
+
- Wer: 0.5423
|
21 |
+
- Cer: 0.1998
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0005
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_ratio: 0.25
|
47 |
+
- num_epochs: 60.0
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
54 |
+
| 3985.5875 | 1.0 | 1080 | 283.6873 | 0.5933 | 0.1666 |
|
55 |
+
| 665.3671 | 2.0 | 2160 | 223.1731 | 0.3818 | 0.1186 |
|
56 |
+
| 481.9958 | 3.0 | 3240 | 223.3375 | 0.4375 | 0.1354 |
|
57 |
+
| 442.5208 | 4.0 | 4320 | 236.0903 | 0.4233 | 0.1444 |
|
58 |
+
| 421.2154 | 5.0 | 5400 | 304.9387 | 0.4626 | 0.1564 |
|
59 |
+
| 431.8639 | 6.0 | 6480 | 298.5758 | 0.5199 | 0.1793 |
|
60 |
+
| 444.0917 | 7.0 | 7560 | 347.2079 | 0.5570 | 0.1988 |
|
61 |
+
| 451.4575 | 8.0 | 8640 | 375.0053 | 0.5731 | 0.2092 |
|
62 |
+
| 445.6943 | 9.0 | 9720 | 360.6095 | 0.6165 | 0.2406 |
|
63 |
+
| 457.5267 | 10.0 | 10800 | 413.6321 | 0.6510 | 0.2522 |
|
64 |
+
| 468.0921 | 11.0 | 11880 | 405.5587 | 0.6422 | 0.2447 |
|
65 |
+
| 469.1014 | 12.0 | 12960 | 423.7671 | 0.6370 | 0.2496 |
|
66 |
+
| 472.7028 | 13.0 | 14040 | 476.4250 | 0.6583 | 0.2521 |
|
67 |
+
| 477.4817 | 14.0 | 15120 | 431.7321 | 0.6496 | 0.2523 |
|
68 |
+
| 476.1046 | 15.0 | 16200 | 456.8628 | 0.6735 | 0.2686 |
|
69 |
+
| 478.12 | 16.0 | 17280 | 477.7070 | 0.6667 | 0.2542 |
|
70 |
+
| 439.3815 | 17.0 | 18360 | 441.1053 | 0.6577 | 0.2600 |
|
71 |
+
| 406.8238 | 18.0 | 19440 | 417.4709 | 0.6793 | 0.2496 |
|
72 |
+
| 381.221 | 19.0 | 20520 | 385.2146 | 0.6340 | 0.2346 |
|
73 |
+
| 349.7026 | 20.0 | 21600 | 417.8041 | 0.6319 | 0.2451 |
|
74 |
+
| 336.5142 | 21.0 | 22680 | 446.5249 | 0.6700 | 0.2432 |
|
75 |
+
| 316.0003 | 22.0 | 23760 | 414.9000 | 0.6574 | 0.2296 |
|
76 |
+
| 301.4025 | 23.0 | 24840 | 435.7232 | 0.6242 | 0.2294 |
|
77 |
+
| 276.272 | 24.0 | 25920 | 447.3780 | 0.6108 | 0.2273 |
|
78 |
+
| 267.6378 | 25.0 | 27000 | 412.0445 | 0.6068 | 0.2430 |
|
79 |
+
| 249.7945 | 26.0 | 28080 | 411.8222 | 0.6144 | 0.2386 |
|
80 |
+
| 238.2421 | 27.0 | 29160 | 403.0204 | 0.6283 | 0.2365 |
|
81 |
+
| 226.9799 | 28.0 | 30240 | 399.3009 | 0.6117 | 0.2249 |
|
82 |
+
| 209.7066 | 29.0 | 31320 | 418.8339 | 0.5925 | 0.2297 |
|
83 |
+
| 200.3202 | 30.0 | 32400 | 411.5076 | 0.6037 | 0.2221 |
|
84 |
+
| 193.5312 | 31.0 | 33480 | 421.6948 | 0.5925 | 0.2199 |
|
85 |
+
| 186.5759 | 32.0 | 34560 | 403.4677 | 0.5838 | 0.2202 |
|
86 |
+
| 176.4434 | 33.0 | 35640 | 449.6694 | 0.5985 | 0.2256 |
|
87 |
+
| 164.8203 | 34.0 | 36720 | 373.5114 | 0.5936 | 0.2238 |
|
88 |
+
| 153.8149 | 35.0 | 37800 | 387.5101 | 0.5713 | 0.2196 |
|
89 |
+
| 148.2955 | 36.0 | 38880 | 422.5177 | 0.5836 | 0.2219 |
|
90 |
+
| 139.206 | 37.0 | 39960 | 424.9959 | 0.5836 | 0.2233 |
|
91 |
+
| 137.3851 | 38.0 | 41040 | 428.6248 | 0.5863 | 0.2188 |
|
92 |
+
| 128.706 | 39.0 | 42120 | 420.8113 | 0.5759 | 0.2173 |
|
93 |
+
| 122.1991 | 40.0 | 43200 | 449.3417 | 0.5792 | 0.2218 |
|
94 |
+
| 114.7006 | 41.0 | 44280 | 472.1264 | 0.5743 | 0.2232 |
|
95 |
+
| 112.9208 | 42.0 | 45360 | 484.6367 | 0.5870 | 0.2134 |
|
96 |
+
| 104.3684 | 43.0 | 46440 | 475.1778 | 0.5617 | 0.2078 |
|
97 |
+
| 101.3417 | 44.0 | 47520 | 438.1502 | 0.5639 | 0.2081 |
|
98 |
+
| 93.9768 | 45.0 | 48600 | 450.4065 | 0.5582 | 0.2067 |
|
99 |
+
| 95.7108 | 46.0 | 49680 | 471.1706 | 0.5646 | 0.2114 |
|
100 |
+
| 85.0469 | 47.0 | 50760 | 466.9779 | 0.5614 | 0.2078 |
|
101 |
+
| 86.9859 | 48.0 | 51840 | 457.3221 | 0.5639 | 0.2069 |
|
102 |
+
| 82.6203 | 49.0 | 52920 | 467.1034 | 0.5559 | 0.2060 |
|
103 |
+
| 76.6465 | 50.0 | 54000 | 488.0355 | 0.5606 | 0.2075 |
|
104 |
+
| 72.2897 | 51.0 | 55080 | 506.8006 | 0.5529 | 0.2017 |
|
105 |
+
| 66.3217 | 52.0 | 56160 | 513.1782 | 0.5503 | 0.2066 |
|
106 |
+
| 63.3613 | 53.0 | 57240 | 509.8887 | 0.5571 | 0.2055 |
|
107 |
+
| 63.2432 | 54.0 | 58320 | 532.0458 | 0.5603 | 0.2093 |
|
108 |
+
| 58.8891 | 55.0 | 59400 | 529.6933 | 0.5526 | 0.2062 |
|
109 |
+
| 64.8119 | 56.0 | 60480 | 530.6396 | 0.5466 | 0.2025 |
|
110 |
+
| 53.2317 | 57.0 | 61560 | 548.7179 | 0.5415 | 0.1994 |
|
111 |
+
| 52.8465 | 58.0 | 62640 | 547.5447 | 0.5399 | 0.2007 |
|
112 |
+
| 50.4224 | 59.0 | 63720 | 545.9059 | 0.5426 | 0.2007 |
|
113 |
+
| 50.2867 | 60.0 | 64800 | 551.5420 | 0.5423 | 0.1998 |
|
114 |
+
|
115 |
+
|
116 |
+
### Framework versions
|
117 |
+
|
118 |
+
- Transformers 4.48.3
|
119 |
+
- Pytorch 2.5.1
|
120 |
+
- Datasets 3.2.0
|
121 |
+
- Tokenizers 0.21.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1261996080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a92e673f720166b6a55433f4c5ec70b7d4d5dd8d7e567c6e59a406f9294525f
|
3 |
size 1261996080
|