Hugging Face's logo

MohamedAhmedAE
/
OpenAI_Clip_Roco_ALL_V1

Safetensors
clip
Generated from Trainer
Model card Files Community
MohamedAhmedAE commited on
Commit
16121a9
•
1 Parent(s): 7f37f7d

Model save

Browse files
Files changed (3) hide show
  1. README.md +12 -3
  2. last-checkpoint/trainer_state.json +0 -0
  3. training_args.bin +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 3.8440
17
 
18
  ## Model description
19
 
@@ -33,8 +33,8 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 5e-05
36
- - train_batch_size: 256
37
- - eval_batch_size: 256
38
  - seed: 2
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: cosine
@@ -541,6 +541,15 @@ The following hyperparameters were used during training:
541
  | 0.3182 | 22.1943 | 494000 | 3.8617 |
542
  | 0.3633 | 22.2392 | 495000 | 3.8879 |
543
  | 0.3282 | 22.2841 | 496000 | 3.8440 |
 
 
 
 
 
 
 
 
 
544
 
545
 
546
  ### Framework versions
 
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 1.2898
17
 
18
  ## Model description
19
 
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 5e-05
36
+ - train_batch_size: 32
37
+ - eval_batch_size: 32
38
  - seed: 2
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: cosine
 
541
  | 0.3182 | 22.1943 | 494000 | 3.8617 |
542
  | 0.3633 | 22.2392 | 495000 | 3.8879 |
543
  | 0.3282 | 22.2841 | 496000 | 3.8440 |
544
+ | 0.4121 | 29.7712 | 497000 | 1.3002 |
545
+ | 0.4185 | 29.8311 | 498000 | 1.3007 |
546
+ | 0.4 | 29.8910 | 499000 | 1.2910 |
547
+ | 0.4009 | 29.9509 | 500000 | 1.2899 |
548
+ | 0.3744 | 30.0108 | 501000 | 1.2981 |
549
+ | 0.3691 | 30.0707 | 502000 | 1.2914 |
550
+ | 0.3775 | 30.1306 | 503000 | 1.2877 |
551
+ | 0.3604 | 30.1905 | 504000 | 1.2967 |
552
+ | 0.3934 | 30.2504 | 505000 | 1.2898 |
553
 
554
 
555
  ### Framework versions
last-checkpoint/trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90522abbdd95ad74158c8fe9b382e088ef9a6cb34be2bf478efc3daa7d826730
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39526ab562e7eecfc574042300c36bed45d9a29bbf93315c727e39bef593c57a
3
  size 5240