Hugging Face's logo

mateoguaman
/
paligemma_racer

Image-Text-to-Text
Transformers
Safetensors
paligemma
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
mateoguaman commited on
Commit
e6ed6fb
·
verified ·
1 Parent(s): ea89f50

End of training

Browse files
Files changed (4) hide show
  1. README.md +155 -0
  2. generation_config.json +7 -0
  3. model-00001-of-00002.safetensors +1 -1
  4. model-00002-of-00002.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: gemma
4
+ base_model: google/paligemma-3b-pt-224
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: paligemma_racer
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
+ # paligemma_racer
16
+
17
+ This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 2.9411
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
44
+ - optimizer: Use adamw_hf 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_steps: 100
47
+ - num_epochs: 2
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:------:|:----:|:---------------:|
53
+ | 13.5721 | 0.0209 | 50 | 7.2124 |
54
+ | 5.9601 | 0.0419 | 100 | 5.0726 |
55
+ | 4.731 | 0.0628 | 150 | 4.4045 |
56
+ | 4.2565 | 0.0837 | 200 | 4.0800 |
57
+ | 4.0418 | 0.1047 | 250 | 3.8702 |
58
+ | 3.866 | 0.1256 | 300 | 3.7370 |
59
+ | 3.6864 | 0.1465 | 350 | 3.5834 |
60
+ | 3.649 | 0.1675 | 400 | 3.5023 |
61
+ | 3.572 | 0.1884 | 450 | 3.4903 |
62
+ | 3.4765 | 0.2093 | 500 | 3.4307 |
63
+ | 3.406 | 0.2302 | 550 | 3.3801 |
64
+ | 3.3997 | 0.2512 | 600 | 3.3027 |
65
+ | 3.3602 | 0.2721 | 650 | 3.2871 |
66
+ | 3.2852 | 0.2930 | 700 | 3.2509 |
67
+ | 3.3183 | 0.3140 | 750 | 3.2354 |
68
+ | 3.3281 | 0.3349 | 800 | 3.2133 |
69
+ | 3.2545 | 0.3558 | 850 | 3.2098 |
70
+ | 3.3173 | 0.3768 | 900 | 3.1909 |
71
+ | 3.1993 | 0.3977 | 950 | 3.1646 |
72
+ | 3.1705 | 0.4186 | 1000 | 3.1401 |
73
+ | 3.1976 | 0.4396 | 1050 | 3.1217 |
74
+ | 3.1514 | 0.4605 | 1100 | 3.1340 |
75
+ | 3.1832 | 0.4814 | 1150 | 3.1282 |
76
+ | 3.1222 | 0.5024 | 1200 | 3.0997 |
77
+ | 3.1003 | 0.5233 | 1250 | 3.0788 |
78
+ | 3.0833 | 0.5442 | 1300 | 3.0735 |
79
+ | 3.099 | 0.5651 | 1350 | 3.0665 |
80
+ | 3.1295 | 0.5861 | 1400 | 3.0534 |
81
+ | 3.0962 | 0.6070 | 1450 | 3.0392 |
82
+ | 3.0589 | 0.6279 | 1500 | 3.0325 |
83
+ | 3.075 | 0.6489 | 1550 | 3.0311 |
84
+ | 3.034 | 0.6698 | 1600 | 3.0461 |
85
+ | 3.0333 | 0.6907 | 1650 | 3.0190 |
86
+ | 3.0494 | 0.7117 | 1700 | 3.0174 |
87
+ | 3.071 | 0.7326 | 1750 | 3.0123 |
88
+ | 3.0147 | 0.7535 | 1800 | 3.0020 |
89
+ | 3.0114 | 0.7745 | 1850 | 3.0074 |
90
+ | 3.0635 | 0.7954 | 1900 | 3.0224 |
91
+ | 2.9939 | 0.8163 | 1950 | 2.9942 |
92
+ | 3.0373 | 0.8373 | 2000 | 2.9888 |
93
+ | 2.998 | 0.8582 | 2050 | 2.9905 |
94
+ | 3.0004 | 0.8791 | 2100 | 2.9883 |
95
+ | 2.9477 | 0.9001 | 2150 | 2.9887 |
96
+ | 2.9837 | 0.9210 | 2200 | 2.9830 |
97
+ | 2.9501 | 0.9419 | 2250 | 2.9788 |
98
+ | 3.0235 | 0.9628 | 2300 | 2.9877 |
99
+ | 3.0083 | 0.9838 | 2350 | 2.9723 |
100
+ | 2.9368 | 1.0047 | 2400 | 2.9775 |
101
+ | 2.9975 | 1.0256 | 2450 | 2.9712 |
102
+ | 2.9089 | 1.0466 | 2500 | 2.9616 |
103
+ | 2.9285 | 1.0675 | 2550 | 2.9669 |
104
+ | 2.9627 | 1.0884 | 2600 | 2.9668 |
105
+ | 2.9195 | 1.1094 | 2650 | 2.9683 |
106
+ | 2.9319 | 1.1303 | 2700 | 2.9607 |
107
+ | 2.9009 | 1.1512 | 2750 | 2.9592 |
108
+ | 2.9486 | 1.1722 | 2800 | 2.9525 |
109
+ | 2.9416 | 1.1931 | 2850 | 2.9532 |
110
+ | 2.9223 | 1.2140 | 2900 | 2.9547 |
111
+ | 2.9257 | 1.2350 | 2950 | 2.9520 |
112
+ | 2.9182 | 1.2559 | 3000 | 2.9516 |
113
+ | 2.9255 | 1.2768 | 3050 | 2.9502 |
114
+ | 2.9113 | 1.2977 | 3100 | 2.9579 |
115
+ | 2.9165 | 1.3187 | 3150 | 2.9584 |
116
+ | 2.8901 | 1.3396 | 3200 | 2.9528 |
117
+ | 2.921 | 1.3605 | 3250 | 2.9470 |
118
+ | 2.9299 | 1.3815 | 3300 | 2.9481 |
119
+ | 2.9728 | 1.4024 | 3350 | 2.9458 |
120
+ | 2.919 | 1.4233 | 3400 | 2.9446 |
121
+ | 2.9132 | 1.4443 | 3450 | 2.9446 |
122
+ | 2.9178 | 1.4652 | 3500 | 2.9486 |
123
+ | 2.9293 | 1.4861 | 3550 | 2.9450 |
124
+ | 2.9514 | 1.5071 | 3600 | 2.9431 |
125
+ | 2.9099 | 1.5280 | 3650 | 2.9444 |
126
+ | 2.9292 | 1.5489 | 3700 | 2.9449 |
127
+ | 2.9336 | 1.5699 | 3750 | 2.9445 |
128
+ | 2.8772 | 1.5908 | 3800 | 2.9446 |
129
+ | 2.9389 | 1.6117 | 3850 | 2.9444 |
130
+ | 2.9618 | 1.6327 | 3900 | 2.9448 |
131
+ | 2.9721 | 1.6536 | 3950 | 2.9425 |
132
+ | 2.9052 | 1.6745 | 4000 | 2.9406 |
133
+ | 2.9245 | 1.6954 | 4050 | 2.9448 |
134
+ | 2.9196 | 1.7164 | 4100 | 2.9429 |
135
+ | 2.9622 | 1.7373 | 4150 | 2.9408 |
136
+ | 2.9199 | 1.7582 | 4200 | 2.9394 |
137
+ | 2.9114 | 1.7792 | 4250 | 2.9385 |
138
+ | 2.9548 | 1.8001 | 4300 | 2.9402 |
139
+ | 2.9263 | 1.8210 | 4350 | 2.9405 |
140
+ | 2.9079 | 1.8420 | 4400 | 2.9414 |
141
+ | 2.9144 | 1.8629 | 4450 | 2.9367 |
142
+ | 2.8985 | 1.8838 | 4500 | 2.9412 |
143
+ | 2.8942 | 1.9048 | 4550 | 2.9446 |
144
+ | 2.91 | 1.9257 | 4600 | 2.9424 |
145
+ | 2.8951 | 1.9466 | 4650 | 2.9414 |
146
+ | 2.9054 | 1.9676 | 4700 | 2.9411 |
147
+ | 2.8909 | 1.9885 | 4750 | 2.9411 |
148
+
149
+
150
+ ### Framework versions
151
+
152
+ - Transformers 4.46.3
153
+ - Pytorch 2.5.1
154
+ - Datasets 3.1.0
155
+ - Tokenizers 0.20.3
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.46.3"
7
+ }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:507ddb0044284bb091c9de34dcbb7eb9f5ec2e5bfacaa00784aaf34d5e5f65a7
3
  size 4985044392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23c6ec9637aea96c18202016bb5bc476fe1754c98c3e3fd8d047c83095ca3e6
3
  size 4985044392
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cb1e4072cf01c91bacfa57d972a45296c68642f645f57f4c6ad491dbcf44d96
3
  size 861970608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:546ef304978193682bb50c3e3798dd40ba7625c8944da971ac4d4a6be2b612fd
3
  size 861970608