End of training

README.md

@@ -10,15 +10,31 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/uq5hn82n)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/mg3h1yqv)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/h2rqrxs0)
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/bjp71783)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/m11loi02)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/t03jb8oo)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/jnf23mqy)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/gekjsx8s)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/1tnxd2m4)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/cyprvgmj)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/mewgojjx)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/9amqiizn)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/amv3g9hh)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/8zuxk7bv)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/2vcog7yz)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/34tiq5ro)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/fn8tubfv)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/xuc8mt5z)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bileldjemel/uncategorized/runs/lgyvvp3g)
 # clip-hugging-face-finetuned
 
 This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0000
+- eval_loss: 3.4109
+- eval_runtime: 2.1433
+- eval_samples_per_second: 69.985
+- eval_steps_per_second: 2.333
+- epoch: 1.3333
+- step: 16
 
 ## Model description
 
@@ -37,29 +53,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1.2963514383416616e-06
-- train_batch_size: 2
-- eval_batch_size: 2
+- learning_rate: 0.0009878479541726164
+- train_batch_size: 128
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2.0
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.0002        | 0.2   | 1    | 0.0000          |
-| 0.0           | 0.4   | 2    | 0.0000          |
-| 0.0003        | 0.6   | 3    | 0.0000          |
-| 0.0           | 0.8   | 4    | 0.0000          |
-| 0.0           | 1.0   | 5    | 0.0000          |
-| 0.0           | 1.2   | 6    | 0.0000          |
-| 0.0           | 1.4   | 7    | 0.0000          |
-| 0.0016        | 1.6   | 8    | 0.0000          |
-| 0.0           | 1.8   | 9    | 0.0000          |
-| 0.0           | 2.0   | 10   | 0.0000          |
-
+- num_epochs: 3.0
 
 ### Framework versions
 

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 2.0,
-    "eval_loss": 0.5955778956413269,
-    "eval_runtime": 6.1056,
-    "eval_samples_per_second": 1.638,
-    "eval_steps_per_second": 0.819,
+    "eval_loss": 0.0010517959017306566,
+    "eval_runtime": 3.3687,
+    "eval_samples_per_second": 1.187,
+    "eval_steps_per_second": 0.297,
     "total_flos": 5816699796600.0,
     "train_loss": 1.3652541448495217,
     "train_runtime": 216.8469,

eval_results.json

@@ -1,7 +1,6 @@
 {
-    "epoch": 2.0,
-    "eval_loss": 0.5955778956413269,
-    "eval_runtime": 6.1056,
-    "eval_samples_per_second": 1.638,
-    "eval_steps_per_second": 0.819
+    "eval_loss": 0.0010517959017306566,
+    "eval_runtime": 3.3687,
+    "eval_samples_per_second": 1.187,
+    "eval_steps_per_second": 0.297
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c2287af2162f5f961e6236c1fbc8fcdcdd4c626d54891b337176e17ac52fad4
+oid sha256:ad4e128ff73124878398616e0553c55f05b0993e43ba677d6a9e68289dba7574
 size 605156676

runs/May08_15-03-56_52ac9e18b79c/events.out.tfevents.1715180646.52ac9e18b79c.6911.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ec376575259fb4d5799ea1a489f7a0f914dc36f2604c2bf14be69c085d4e8a
+size 297

runs/May08_18-23-35_2e4200763c33/events.out.tfevents.1715192913.2e4200763c33.2033.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb6db8b60003d6ec0b8eb48ec25618c6619d4183e3ef6980d4f1af825e25a09
+size 297

runs/May08_19-52-55_2e4200763c33/events.out.tfevents.1715198757.2e4200763c33.23399.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e484637443c9f3b2742fbf5fed53c21ac1f739b92c82c54110a0cc87e8e02e75
+size 297

runs/May08_20-12-51_2e4200763c33/events.out.tfevents.1715199448.2e4200763c33.28255.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4df300e9bf6f079373060761e8ef451b3fe2ef525aea5e6e96c6c7d27d7d88
+size 297

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e159b8d7a625cd493be84b9164be652ab60de60a0e69a3546253c7e27f91e88
+oid sha256:fd005232ba58b22028f3bbdc312e8366481d51b4fec5674d8bdf3e7702c88a42
 size 5112