🍻 cheers
Browse files- README.md +3 -2
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +58 -0
README.md
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model: google/vit-base-patch16-224
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# vit-base-plankton
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- imagefolder
|
|
|
|
| 16 |
|
| 17 |
# vit-base-plankton
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the beans dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 6.762570523759411e+16,
|
| 4 |
+
"train_loss": 2.928572859082903,
|
| 5 |
+
"train_runtime": 1229.5876,
|
| 6 |
+
"train_samples_per_second": 0.709,
|
| 7 |
+
"train_steps_per_second": 0.046
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 6.762570523759411e+16,
|
| 4 |
+
"train_loss": 2.928572859082903,
|
| 5 |
+
"train_runtime": 1229.5876,
|
| 6 |
+
"train_samples_per_second": 0.709,
|
| 7 |
+
"train_steps_per_second": 0.046
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 56,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36,
|
| 13 |
+
"learning_rate": 0.00016428571428571428,
|
| 14 |
+
"loss": 3.6178,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.71,
|
| 19 |
+
"learning_rate": 0.00012857142857142858,
|
| 20 |
+
"loss": 3.2104,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.07,
|
| 25 |
+
"learning_rate": 9.285714285714286e-05,
|
| 26 |
+
"loss": 2.8772,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.43,
|
| 31 |
+
"learning_rate": 5.714285714285714e-05,
|
| 32 |
+
"loss": 2.6572,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.79,
|
| 37 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 38 |
+
"loss": 2.554,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"step": 56,
|
| 44 |
+
"total_flos": 6.762570523759411e+16,
|
| 45 |
+
"train_loss": 2.928572859082903,
|
| 46 |
+
"train_runtime": 1229.5876,
|
| 47 |
+
"train_samples_per_second": 0.709,
|
| 48 |
+
"train_steps_per_second": 0.046
|
| 49 |
+
}
|
| 50 |
+
],
|
| 51 |
+
"logging_steps": 10,
|
| 52 |
+
"max_steps": 56,
|
| 53 |
+
"num_train_epochs": 2,
|
| 54 |
+
"save_steps": 100,
|
| 55 |
+
"total_flos": 6.762570523759411e+16,
|
| 56 |
+
"trial_name": null,
|
| 57 |
+
"trial_params": null
|
| 58 |
+
}
|