End of training

README.md

@@ -2,14 +2,14 @@
 tags:
 - generated_from_trainer
 model-index:
-- name: outputs
+- name: fasterrcnn_clip
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# outputs
+# fasterrcnn_clip
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 
@@ -34,12 +34,12 @@ The following hyperparameters were used during training:
 - train_batch_size: 24
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 48
+- 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: 1000
+- training_steps: 10000
 - mixed_precision_training: Native AMP
 
 ### Training results

config.json

@@ -3,6 +3,7 @@
     "TextCLIP"
   ],
   "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 sha256:91d6cc32ed3a9d0e1bc3a337cb399fc89e50a4985ec6948937331cd30aff3f63
+oid sha256:1837b1cf6618cf9666d1b09805108edfdc0c6a916f7174a649e487a2baf20618
 size 836369868

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b588fa4e4af2f13764e8dee036293c46659d74216aadfc7e7655cd871e55aad2
+oid sha256:513c98a40f02d8123130b4d017720227c14fad5ed456734675981c298e494629
 size 4920