Commit
•
1aff4cd
1
Parent(s):
e10f245
End of training
Browse files
README.md
CHANGED
@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- eval_loss: 0.
|
21 |
-
- eval_accuracy: 0.
|
22 |
-
- eval_runtime:
|
23 |
-
- eval_samples_per_second: 97.
|
24 |
-
- eval_steps_per_second: 6.
|
25 |
-
- epoch:
|
26 |
-
- step:
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- eval_loss: 0.7466
|
21 |
+
- eval_accuracy: 0.8160
|
22 |
+
- eval_runtime: 154.8193
|
23 |
+
- eval_samples_per_second: 97.856
|
24 |
+
- eval_steps_per_second: 6.117
|
25 |
+
- epoch: 25.34
|
26 |
+
- step: 24000
|
27 |
|
28 |
## Model description
|
29 |
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343528508
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02e9b83bfe540be2a40e1ad337fc2e448fa90516adb14b782643f3ac29c29f45
|
3 |
size 343528508
|
runs/Feb05_03-08-58_983d148b451b/events.out.tfevents.1707102539.983d148b451b.26.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a40a78d436c99350177ecd5e4e0d4d09ae65322b292a9cd0dd9f611ae79a5da7
|
3 |
+
size 20893
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.8201980198019801,
|
3 |
"best_model_checkpoint": "food-image-classification/checkpoint-22000",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -352,6 +352,21 @@
|
|
352 |
"eval_samples_per_second": 97.283,
|
353 |
"eval_steps_per_second": 6.081,
|
354 |
"step": 23000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
355 |
}
|
356 |
],
|
357 |
"logging_steps": 1000,
|
@@ -359,7 +374,7 @@
|
|
359 |
"num_input_tokens_seen": 0,
|
360 |
"num_train_epochs": 500,
|
361 |
"save_steps": 1000,
|
362 |
-
"total_flos": 1.
|
363 |
"train_batch_size": 16,
|
364 |
"trial_name": null,
|
365 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.8201980198019801,
|
3 |
"best_model_checkpoint": "food-image-classification/checkpoint-22000",
|
4 |
+
"epoch": 25.343189017951424,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 24000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
352 |
"eval_samples_per_second": 97.283,
|
353 |
"eval_steps_per_second": 6.081,
|
354 |
"step": 23000
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 25.34,
|
358 |
+
"learning_rate": 2.5343189017951425e-05,
|
359 |
+
"loss": 0.3574,
|
360 |
+
"step": 24000
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 25.34,
|
364 |
+
"eval_accuracy": 0.815973597359736,
|
365 |
+
"eval_loss": 0.7465734481811523,
|
366 |
+
"eval_runtime": 154.8193,
|
367 |
+
"eval_samples_per_second": 97.856,
|
368 |
+
"eval_steps_per_second": 6.117,
|
369 |
+
"step": 24000
|
370 |
}
|
371 |
],
|
372 |
"logging_steps": 1000,
|
|
|
374 |
"num_input_tokens_seen": 0,
|
375 |
"num_train_epochs": 500,
|
376 |
"save_steps": 1000,
|
377 |
+
"total_flos": 1.1911779784977408e+20,
|
378 |
"train_batch_size": 16,
|
379 |
"trial_name": null,
|
380 |
"trial_params": null
|