Model save
Browse files
README.md
CHANGED
|
@@ -16,12 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
| 20 |
-
- eval_runtime: 61.0128
|
| 21 |
-
- eval_samples_per_second: 1.328
|
| 22 |
-
- eval_steps_per_second: 0.672
|
| 23 |
-
- epoch: 4.0
|
| 24 |
-
- step: 200
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -40,7 +35,7 @@ More information needed
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
-
- learning_rate:
|
| 44 |
- train_batch_size: 2
|
| 45 |
- eval_batch_size: 2
|
| 46 |
- seed: 42
|
|
@@ -48,7 +43,38 @@ The following hyperparameters were used during training:
|
|
| 48 |
- total_train_batch_size: 8
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
### Framework versions
|
| 54 |
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1043
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-06
|
| 39 |
- train_batch_size: 2
|
| 40 |
- eval_batch_size: 2
|
| 41 |
- seed: 42
|
|
|
|
| 43 |
- total_train_batch_size: 8
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 5
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 0.1502 | 0.2 | 10 | 0.1155 |
|
| 53 |
+
| 0.1414 | 0.4 | 20 | 0.1136 |
|
| 54 |
+
| 0.1481 | 0.6 | 30 | 0.1134 |
|
| 55 |
+
| 0.1384 | 0.8 | 40 | 0.1121 |
|
| 56 |
+
| 0.1472 | 1.0 | 50 | 0.1112 |
|
| 57 |
+
| 0.1357 | 1.2 | 60 | 0.1108 |
|
| 58 |
+
| 0.124 | 1.4 | 70 | 0.1102 |
|
| 59 |
+
| 0.1495 | 1.6 | 80 | 0.1096 |
|
| 60 |
+
| 0.1438 | 1.8 | 90 | 0.1090 |
|
| 61 |
+
| 0.1394 | 2.0 | 100 | 0.1078 |
|
| 62 |
+
| 0.1285 | 2.2 | 110 | 0.1071 |
|
| 63 |
+
| 0.131 | 2.4 | 120 | 0.1071 |
|
| 64 |
+
| 0.1375 | 2.6 | 130 | 0.1068 |
|
| 65 |
+
| 0.1243 | 2.8 | 140 | 0.1061 |
|
| 66 |
+
| 0.138 | 3.0 | 150 | 0.1056 |
|
| 67 |
+
| 0.1386 | 3.2 | 160 | 0.1055 |
|
| 68 |
+
| 0.1325 | 3.4 | 170 | 0.1052 |
|
| 69 |
+
| 0.1252 | 3.6 | 180 | 0.1052 |
|
| 70 |
+
| 0.1371 | 3.8 | 190 | 0.1049 |
|
| 71 |
+
| 0.122 | 4.0 | 200 | 0.1048 |
|
| 72 |
+
| 0.1149 | 4.2 | 210 | 0.1046 |
|
| 73 |
+
| 0.1318 | 4.4 | 220 | 0.1044 |
|
| 74 |
+
| 0.1169 | 4.6 | 230 | 0.1043 |
|
| 75 |
+
| 0.1412 | 4.8 | 240 | 0.1041 |
|
| 76 |
+
| 0.1514 | 5.0 | 250 | 0.1043 |
|
| 77 |
+
|
| 78 |
|
| 79 |
### Framework versions
|
| 80 |
|