End of training

README.md

@@ -31,15 +31,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 24
+- train_batch_size: 128
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 96
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
-- training_steps: 10000
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results

config.json

@@ -1,9 +1,8 @@
 {
   "architectures": [
-    "TextCLIP"
+    "GroupModel"
   ],
   "logit_scale_init_value": 2.6592,
-  "model_type": "myclip",
   "projection_dim": 512,
   "text_model": "google-bert/bert-base-multilingual-uncased",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1837b1cf6618cf9666d1b09805108edfdc0c6a916f7174a649e487a2baf20618
-size 836369868
+oid sha256:f54b40805b108eaf408365a56fc8b73843f889be2fa0e4676b8713b2b37812a7
+size 673120508

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:513c98a40f02d8123130b4d017720227c14fad5ed456734675981c298e494629
+oid sha256:7071d1a628848de3677ea2551d88cb978347bbf5c2a91bbc3f6acdc72103f385
 size 4920