GQA[:100000]
Browse files- README.md +131 -0
- emissions.csv +2 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: dandelin/vilt-b32-mlm
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: vilt_finetuned_100000
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# vilt_finetuned_100000
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.2049
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 3
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
+
| 148.4684 | 0.04 | 250 | 5.6972 |
|
50 |
+
| 5.0473 | 0.08 | 500 | 4.5986 |
|
51 |
+
| 4.4685 | 0.12 | 750 | 4.2115 |
|
52 |
+
| 4.0423 | 0.16 | 1000 | 3.8991 |
|
53 |
+
| 3.8019 | 0.2 | 1250 | 3.7080 |
|
54 |
+
| 3.6731 | 0.24 | 1500 | 3.5319 |
|
55 |
+
| 3.5226 | 0.28 | 1750 | 3.4277 |
|
56 |
+
| 3.3556 | 0.32 | 2000 | 3.3546 |
|
57 |
+
| 3.279 | 0.36 | 2250 | 3.2592 |
|
58 |
+
| 3.2406 | 0.4 | 2500 | 3.1792 |
|
59 |
+
| 3.1275 | 0.44 | 2750 | 3.1014 |
|
60 |
+
| 3.0569 | 0.48 | 3000 | 3.0938 |
|
61 |
+
| 3.0484 | 0.52 | 3250 | 2.9939 |
|
62 |
+
| 2.9883 | 0.56 | 3500 | 2.9230 |
|
63 |
+
| 2.9351 | 0.6 | 3750 | 2.8902 |
|
64 |
+
| 2.8526 | 0.64 | 4000 | 2.8242 |
|
65 |
+
| 2.8469 | 0.68 | 4250 | 2.8069 |
|
66 |
+
| 2.7228 | 0.72 | 4500 | 2.7304 |
|
67 |
+
| 2.6549 | 0.76 | 4750 | 2.6875 |
|
68 |
+
| 2.6304 | 0.8 | 5000 | 2.6461 |
|
69 |
+
| 2.6239 | 0.84 | 5250 | 2.6117 |
|
70 |
+
| 2.6334 | 0.88 | 5500 | 2.5914 |
|
71 |
+
| 2.622 | 0.92 | 5750 | 2.5320 |
|
72 |
+
| 2.5581 | 0.96 | 6000 | 2.5028 |
|
73 |
+
| 2.536 | 1.0 | 6250 | 2.5663 |
|
74 |
+
| 2.3565 | 1.04 | 6500 | 2.4770 |
|
75 |
+
| 2.2907 | 1.08 | 6750 | 2.4965 |
|
76 |
+
| 2.3328 | 1.12 | 7000 | 2.4514 |
|
77 |
+
| 2.2924 | 1.16 | 7250 | 2.4503 |
|
78 |
+
| 2.2799 | 1.2 | 7500 | 2.4083 |
|
79 |
+
| 2.2477 | 1.24 | 7750 | 2.4246 |
|
80 |
+
| 2.2662 | 1.28 | 8000 | 2.3792 |
|
81 |
+
| 2.2656 | 1.32 | 8250 | 2.3568 |
|
82 |
+
| 2.1932 | 1.36 | 8500 | 2.3682 |
|
83 |
+
| 2.1821 | 1.4 | 8750 | 2.3241 |
|
84 |
+
| 2.1663 | 1.44 | 9000 | 2.3182 |
|
85 |
+
| 2.1017 | 1.48 | 9250 | 2.3225 |
|
86 |
+
| 2.1884 | 1.52 | 9500 | 2.3069 |
|
87 |
+
| 2.1873 | 1.56 | 9750 | 2.2613 |
|
88 |
+
| 2.1094 | 1.6 | 10000 | 2.2730 |
|
89 |
+
| 2.0764 | 1.64 | 10250 | 2.2694 |
|
90 |
+
| 2.1051 | 1.68 | 10500 | 2.2537 |
|
91 |
+
| 2.1283 | 1.72 | 10750 | 2.2434 |
|
92 |
+
| 2.1212 | 1.76 | 11000 | 2.2164 |
|
93 |
+
| 2.0978 | 1.8 | 11250 | 2.2168 |
|
94 |
+
| 1.9994 | 1.84 | 11500 | 2.2015 |
|
95 |
+
| 2.0101 | 1.88 | 11750 | 2.1916 |
|
96 |
+
| 2.0156 | 1.92 | 12000 | 2.1699 |
|
97 |
+
| 2.014 | 1.96 | 12250 | 2.1821 |
|
98 |
+
| 1.9576 | 2.0 | 12500 | 2.1739 |
|
99 |
+
| 1.6838 | 2.04 | 12750 | 2.2527 |
|
100 |
+
| 1.6692 | 2.08 | 13000 | 2.2432 |
|
101 |
+
| 1.6237 | 2.12 | 13250 | 2.2824 |
|
102 |
+
| 1.5776 | 2.16 | 13500 | 2.2619 |
|
103 |
+
| 1.6468 | 2.2 | 13750 | 2.2499 |
|
104 |
+
| 1.6279 | 2.24 | 14000 | 2.2454 |
|
105 |
+
| 1.6277 | 2.28 | 14250 | 2.2624 |
|
106 |
+
| 1.6293 | 2.32 | 14500 | 2.2283 |
|
107 |
+
| 1.6217 | 2.36 | 14750 | 2.2720 |
|
108 |
+
| 1.5921 | 2.4 | 15000 | 2.2643 |
|
109 |
+
| 1.578 | 2.44 | 15250 | 2.2336 |
|
110 |
+
| 1.5559 | 2.48 | 15500 | 2.2311 |
|
111 |
+
| 1.5932 | 2.52 | 15750 | 2.2063 |
|
112 |
+
| 1.5532 | 2.56 | 16000 | 2.2205 |
|
113 |
+
| 1.5736 | 2.6 | 16250 | 2.2141 |
|
114 |
+
| 1.5931 | 2.64 | 16500 | 2.2399 |
|
115 |
+
| 1.5735 | 2.68 | 16750 | 2.2106 |
|
116 |
+
| 1.5161 | 2.72 | 17000 | 2.1973 |
|
117 |
+
| 1.5388 | 2.76 | 17250 | 2.2009 |
|
118 |
+
| 1.5139 | 2.8 | 17500 | 2.2083 |
|
119 |
+
| 1.5298 | 2.84 | 17750 | 2.2030 |
|
120 |
+
| 1.5339 | 2.88 | 18000 | 2.2031 |
|
121 |
+
| 1.4774 | 2.92 | 18250 | 2.2050 |
|
122 |
+
| 1.5067 | 2.96 | 18500 | 2.2074 |
|
123 |
+
| 1.4847 | 3.0 | 18750 | 2.2049 |
|
124 |
+
|
125 |
+
|
126 |
+
### Framework versions
|
127 |
+
|
128 |
+
- Transformers 4.34.1
|
129 |
+
- Pytorch 2.1.0+cu121
|
130 |
+
- Datasets 2.14.6
|
131 |
+
- Tokenizers 0.14.1
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud
|
2 |
+
2023-11-19T06:26:00,codecarbon,ad11c09f-05ac-4540-86fc-7fec506a781c,26997.40578341484,0.40202370333169735,1.4891197567533331e-05,47.5,80.91500000000002,5.838523864746094,0.3561867638851204,0.6891666338081448,0.04374511875727119,1.0890985164505385,United States,USA,virginia,,,Linux-6.2.0-36-generic-x86_64-with-glibc2.37,3.11.5,2.2.2,4,Intel(R) Core(TM) i5-6600K CPU @ 3.50GHz,1,1 x NVIDIA GeForce GTX 1070,-77.3672,38.9841,15.56939697265625,machine,N
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 462520410
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fea209bfcb5d7e0174b1ee5351217da79bae62a564d74f58a7a981279fdff7ff
|
3 |
size 462520410
|