aipib commited on
Commit
35f1b2d
·
verified ·
1 Parent(s): c7a3e8e

aipib/Florence-2-FT-JP-TF2

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/Florence-2-base-ft](https://huggingface.co/microsoft/Florence-2-base-ft) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.5147
20
 
21
  ## Model description
22
 
@@ -41,14 +41,17 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 2
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 2.0532 | 1.0 | 1000 | 1.6798 |
51
- | 1.3575 | 2.0 | 2000 | 1.5147 |
 
 
 
52
 
53
 
54
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/Florence-2-base-ft](https://huggingface.co/microsoft/Florence-2-base-ft) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.3826
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 5
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 2.0416 | 1.0 | 1000 | 1.6576 |
51
+ | 1.3098 | 2.0 | 2000 | 1.4314 |
52
+ | 0.9951 | 3.0 | 3000 | 1.4185 |
53
+ | 0.8056 | 4.0 | 4000 | 1.3705 |
54
+ | 0.6916 | 5.0 | 5000 | 1.3826 |
55
 
56
 
57
  ### Framework versions
config.json CHANGED
@@ -162,7 +162,7 @@
162
  "length_penalty": 1.0,
163
  "max_length": 20,
164
  "min_length": 0,
165
- "model_type": "davit",
166
  "no_repeat_ngram_size": 0,
167
  "num_beam_groups": 1,
168
  "num_beams": 1,
 
162
  "length_penalty": 1.0,
163
  "max_length": 20,
164
  "min_length": 0,
165
+ "model_type": "",
166
  "no_repeat_ngram_size": 0,
167
  "num_beam_groups": 1,
168
  "num_beams": 1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05ef8a80cb5bd11c6c2113d9929f1554076dd25055d568a52b48cb7a1b826be5
3
  size 1083916964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ec0a8fca820bc60686870c0f3abd835ea1fa046ce802c19b75325c43cb9b22
3
  size 1083916964
runs/Dec14_13-54-37_MasanoMacBook-Air-2283.local/events.out.tfevents.1734152081.MasanoMacBook-Air-2283.local ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866a3ecf33f3eccabacbbb7e4df25275af3e142d3044762f8c65688058ab3b7f
3
+ size 10164
runs/Dec14_13-56-14_MasanoMacBook-Air-2283.local/events.out.tfevents.1734152175.MasanoMacBook-Air-2283.local ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd91accd41250b5bcd85cec4fd226c4570d463059fc7ef02334a8bae229edef
3
+ size 12928
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4757babaad877c5e46d227c8e3cd4ff06fdfe2a3834858ddd5ae816fbfad40e7
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd1bb09482a4bf3db32097f29f46672c82a9e5ea0f7f99bb4ad4045550b1afd
3
  size 5304