varcoder
/

resnet-101-finetuned-CivilEng11k

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [microsoft/resnet-101](https://huggingface.co/microsoft/resnet-101) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6763
-- Accuracy: 0.7701
 ## Model description
@@ -37,31 +37,36 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
-- gradient_accumulation_steps: 10
-- total_train_batch_size: 320
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.5769        | 0.98  | 25   | 2.4928          | 0.5270   |
-| 2.2271        | 2.0   | 51   | 2.1844          | 0.5284   |
-| 1.6261        | 2.98  | 76   | 1.4098          | 0.5270   |
-| 1.2715        | 4.0   | 102  | 1.2040          | 0.5799   |
-| 1.1368        | 4.98  | 127  | 1.0044          | 0.6853   |
-| 0.9366        | 6.0   | 153  | 0.8463          | 0.7456   |
-| 0.8249        | 6.98  | 178  | 0.7512          | 0.7686   |
-| 0.7635        | 8.0   | 204  | 0.7079          | 0.7613   |
-| 0.7213        | 8.98  | 229  | 0.6763          | 0.7701   |
-| 0.6905        | 9.8   | 250  | 0.6683          | 0.7676   |
 ### Framework versions
@@ -69,4 +74,4 @@ The following hyperparameters were used during training:
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.0

 This model is a fine-tuned version of [microsoft/resnet-101](https://huggingface.co/microsoft/resnet-101) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.3944
+- Accuracy: 0.8471
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 0.0003
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
+- gradient_accumulation_steps: 15
+- total_train_batch_size: 480
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 15
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.6258        | 1.0   | 17   | 2.5048          | 0.5505   |
+| 2.2924        | 2.0   | 34   | 1.4728          | 0.5275   |
+| 1.452         | 3.0   | 51   | 1.0709          | 0.6951   |
+| 1.0363        | 4.0   | 68   | 0.6555          | 0.7711   |
+| 0.7086        | 5.0   | 85   | 0.4875          | 0.8123   |
+| 0.5185        | 6.0   | 102  | 0.4336          | 0.8358   |
+| 0.4238        | 7.0   | 119  | 0.3962          | 0.8510   |
+| 0.3436        | 8.0   | 136  | 0.3824          | 0.8515   |
+| 0.3185        | 9.0   | 153  | 0.3827          | 0.8515   |
+| 0.3116        | 10.0  | 170  | 0.3789          | 0.8534   |
+| 0.2983        | 11.0  | 187  | 0.3759          | 0.8559   |
+| 0.2703        | 12.0  | 204  | 0.3839          | 0.8480   |
+| 0.2618        | 13.0  | 221  | 0.3831          | 0.8539   |
+| 0.2613        | 14.0  | 238  | 0.3785          | 0.8569   |
+| 0.2428        | 15.0  | 255  | 0.3944          | 0.8471   |
 ### Framework versions
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1
+- Tokenizers 0.15.1

runs/Jan25_03-08-49_173fbb9c3dc5/events.out.tfevents.1706152140.173fbb9c3dc5.3455.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6a2eb5606a57f2ba7948be110bbc1a6d1b038020cd9a6355c1c7b97d6c43f0
-size 11720

 version https://git-lfs.github.com/spec/v1
+oid sha256:2858bf446a795e939c0b1703ab5040a674ef2c1164b866d40eb798437afbcd09
+size 12711