Hugging Face's logo

MoonstoneF
/
kosm-checkpoint

Image-Text-to-Text
Transformers
Safetensors
kosmos-2
Generated from Trainer
Model card Files
xet
 Community
MoonstoneF commited on
Commit
9f7497c
·
verified ·
1 Parent(s): 12d7330

Complete epoch

Browse files
Files changed (3) hide show
  1. README.md +64 -9
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0420
19
 
20
  ## Model description
21
 
@@ -43,17 +43,72 @@ The following hyperparameters were used during training:
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_ratio: 0.1
46
- - training_steps: 1000
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:------:|:----:|:---------------:|
52
- | No log | 0.0497 | 200 | 0.0700 |
53
- | 0.0802 | 0.0993 | 400 | 0.0581 |
54
- | 0.0676 | 0.1490 | 600 | 0.0496 |
55
- | 0.0584 | 0.1986 | 800 | 0.0450 |
56
- | 0.0525 | 0.2483 | 1000 | 0.0420 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0340
19
 
20
  ## Model description
21
 
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 3.0
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:-----:|:---------------:|
52
+ | No log | 0.0497 | 200 | 0.0700 |
53
+ | 0.0802 | 0.0993 | 400 | 0.0581 |
54
+ | 0.0676 | 0.1490 | 600 | 0.0496 |
55
+ | 0.0584 | 0.1986 | 800 | 0.0450 |
56
+ | 0.0582 | 0.2483 | 1000 | 0.0481 |
57
+ | 0.0582 | 0.2979 | 1200 | 0.0486 |
58
+ | 0.0572 | 0.3476 | 1400 | 0.0445 |
59
+ | 0.0537 | 0.3972 | 1600 | 0.0463 |
60
+ | 0.0504 | 0.4469 | 1800 | 0.0421 |
61
+ | 0.0473 | 0.4965 | 2000 | 0.0402 |
62
+ | 0.0473 | 0.5462 | 2200 | 0.0423 |
63
+ | 0.046 | 0.5958 | 2400 | 0.0394 |
64
+ | 0.0448 | 0.6455 | 2600 | 0.0369 |
65
+ | 0.0423 | 0.6951 | 2800 | 0.0378 |
66
+ | 0.0403 | 0.7448 | 3000 | 0.0360 |
67
+ | 0.0403 | 0.7944 | 3200 | 0.0364 |
68
+ | 0.0392 | 0.8441 | 3400 | 0.0352 |
69
+ | 0.0388 | 0.8937 | 3600 | 0.0347 |
70
+ | 0.0375 | 0.9434 | 3800 | 0.0343 |
71
+ | 0.037 | 0.9930 | 4000 | 0.0345 |
72
+ | 0.037 | 1.0427 | 4200 | 0.0355 |
73
+ | 0.03 | 1.0924 | 4400 | 0.0338 |
74
+ | 0.0283 | 1.1420 | 4600 | 0.0349 |
75
+ | 0.0281 | 1.1917 | 4800 | 0.0347 |
76
+ | 0.0288 | 1.2413 | 5000 | 0.0322 |
77
+ | 0.0288 | 1.2910 | 5200 | 0.0331 |
78
+ | 0.0279 | 1.3406 | 5400 | 0.0335 |
79
+ | 0.0272 | 1.3903 | 5600 | 0.0322 |
80
+ | 0.0275 | 1.4399 | 5800 | 0.0338 |
81
+ | 0.0271 | 1.4896 | 6000 | 0.0324 |
82
+ | 0.0271 | 1.5392 | 6200 | 0.0324 |
83
+ | 0.0263 | 1.5889 | 6400 | 0.0320 |
84
+ | 0.0262 | 1.6385 | 6600 | 0.0319 |
85
+ | 0.0264 | 1.6882 | 6800 | 0.0317 |
86
+ | 0.0256 | 1.7378 | 7000 | 0.0322 |
87
+ | 0.0256 | 1.7875 | 7200 | 0.0320 |
88
+ | 0.0255 | 1.8371 | 7400 | 0.0316 |
89
+ | 0.0242 | 1.8868 | 7600 | 0.0327 |
90
+ | 0.0262 | 1.9364 | 7800 | 0.0307 |
91
+ | 0.0252 | 1.9861 | 8000 | 0.0304 |
92
+ | 0.0252 | 2.0357 | 8200 | 0.0343 |
93
+ | 0.0173 | 2.0854 | 8400 | 0.0373 |
94
+ | 0.0148 | 2.1351 | 8600 | 0.0345 |
95
+ | 0.015 | 2.1847 | 8800 | 0.0347 |
96
+ | 0.0148 | 2.2344 | 9000 | 0.0347 |
97
+ | 0.0148 | 2.2840 | 9200 | 0.0354 |
98
+ | 0.0132 | 2.3337 | 9400 | 0.0351 |
99
+ | 0.0136 | 2.3833 | 9600 | 0.0362 |
100
+ | 0.0132 | 2.4330 | 9800 | 0.0360 |
101
+ | 0.0138 | 2.4826 | 10000 | 0.0352 |
102
+ | 0.0138 | 2.5323 | 10200 | 0.0359 |
103
+ | 0.0138 | 2.5819 | 10400 | 0.0348 |
104
+ | 0.0132 | 2.6316 | 10600 | 0.0348 |
105
+ | 0.0129 | 2.6812 | 10800 | 0.0337 |
106
+ | 0.0134 | 2.7309 | 11000 | 0.0354 |
107
+ | 0.0134 | 2.7805 | 11200 | 0.0350 |
108
+ | 0.0132 | 2.8302 | 11400 | 0.0351 |
109
+ | 0.0128 | 2.8798 | 11600 | 0.0350 |
110
+ | 0.013 | 2.9295 | 11800 | 0.0339 |
111
+ | 0.012 | 2.9791 | 12000 | 0.0340 |
112
 
113
 
114
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34bd24e2a0fe242bc370ddcf0ea8dc04f38da941dde875204acb625e2d35b8fc
3
  size 4999738624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012d2a25152c45edff79845380ffeb2bf254fc5f2e4dbbecbd4c0a1d2290e366
3
  size 4999738624
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09da7b3546a2422b851d877a6202d86fecc612a4e03121fc6ec0e8903ae229f
3
  size 1658313704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:050288871bade7de4b6aef3504772b3ab60b70c4220c0b532b7c5b226ec1e9aa
3
  size 1658313704