Commit
•
033d8aa
1
Parent(s):
299077a
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: 153.
|
23 |
-
- eval_samples_per_second: 98.
|
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: 0.7959
|
21 |
+
- eval_accuracy: 0.8075
|
22 |
+
- eval_runtime: 153.9402
|
23 |
+
- eval_samples_per_second: 98.415
|
24 |
+
- eval_steps_per_second: 6.152
|
25 |
+
- epoch: 15.84
|
26 |
+
- step: 15000
|
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:c1b09c44bb650673e03d905cbf2cfecd3c70f20f9fc55fff7e74ce2f82877fdb
|
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:c35e15cb5d3094dc101119d8841eae79ffdf984df25ffddf26551440b87fe5c8
|
3 |
+
size 16501
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "food-image-classification/checkpoint-
|
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,
|
@@ -217,6 +217,21 @@
|
|
217 |
"eval_samples_per_second": 98.61,
|
218 |
"eval_steps_per_second": 6.164,
|
219 |
"step": 14000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
}
|
221 |
],
|
222 |
"logging_steps": 1000,
|
@@ -224,7 +239,7 @@
|
|
224 |
"num_input_tokens_seen": 0,
|
225 |
"num_train_epochs": 500,
|
226 |
"save_steps": 1000,
|
227 |
-
"total_flos":
|
228 |
"train_batch_size": 16,
|
229 |
"trial_name": null,
|
230 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8043564356435644,
|
3 |
+
"best_model_checkpoint": "food-image-classification/checkpoint-14000",
|
4 |
+
"epoch": 15.839493136219641,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 15000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
217 |
"eval_samples_per_second": 98.61,
|
218 |
"eval_steps_per_second": 6.164,
|
219 |
"step": 14000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 15.84,
|
223 |
+
"learning_rate": 1.583949313621964e-05,
|
224 |
+
"loss": 0.6281,
|
225 |
+
"step": 15000
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 15.84,
|
229 |
+
"eval_accuracy": 0.8075247524752476,
|
230 |
+
"eval_loss": 0.7959182858467102,
|
231 |
+
"eval_runtime": 153.9402,
|
232 |
+
"eval_samples_per_second": 98.415,
|
233 |
+
"eval_steps_per_second": 6.152,
|
234 |
+
"step": 15000
|
235 |
}
|
236 |
],
|
237 |
"logging_steps": 1000,
|
|
|
239 |
"num_input_tokens_seen": 0,
|
240 |
"num_train_epochs": 500,
|
241 |
"save_steps": 1000,
|
242 |
+
"total_flos": 7.444901145985229e+19,
|
243 |
"train_batch_size": 16,
|
244 |
"trial_name": null,
|
245 |
"trial_params": null
|