End of training
Browse files
README.md
CHANGED
|
@@ -15,13 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model was trained from scratch on the food101 dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- eval_loss: 0.
|
| 19 |
-
- eval_accuracy: 0.
|
| 20 |
-
- eval_runtime:
|
| 21 |
-
- eval_samples_per_second:
|
| 22 |
-
- eval_steps_per_second: 6.
|
| 23 |
-
- epoch:
|
| 24 |
-
- step:
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 15 |
|
| 16 |
This model was trained from scratch on the food101 dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- eval_loss: 0.3977
|
| 19 |
+
- eval_accuracy: 0.9011
|
| 20 |
+
- eval_runtime: 155.7863
|
| 21 |
+
- eval_samples_per_second: 97.249
|
| 22 |
+
- eval_steps_per_second: 6.079
|
| 23 |
+
- epoch: 43.29
|
| 24 |
+
- step: 41000
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
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 sha256:936ff4ba77db213e42e7d4a6fd31a9bd247c53544aa1bb748716e59e63d2e0fd
|
| 3 |
size 343528508
|
runs/Feb06_02-52-53_2bd6d982b8e8/events.out.tfevents.1707187974.2bd6d982b8e8.26.0
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 sha256:820e67c4db3204ff5ae0466943e6db6c335f3369a0fa30514fffb6ce95775fc4
|
| 3 |
+
size 16738
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9115511551155115,
|
| 3 |
"best_model_checkpoint": "food-image-classification/checkpoint-35000",
|
| 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,
|
|
@@ -607,6 +607,21 @@
|
|
| 607 |
"eval_samples_per_second": 96.95,
|
| 608 |
"eval_steps_per_second": 6.06,
|
| 609 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 1000,
|
|
@@ -614,7 +629,7 @@
|
|
| 614 |
"num_input_tokens_seen": 0,
|
| 615 |
"num_train_epochs": 500,
|
| 616 |
"save_steps": 1000,
|
| 617 |
-
"total_flos":
|
| 618 |
"train_batch_size": 16,
|
| 619 |
"trial_name": null,
|
| 620 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9115511551155115,
|
| 3 |
"best_model_checkpoint": "food-image-classification/checkpoint-35000",
|
| 4 |
+
"epoch": 43.294614572333685,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 41000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 607 |
"eval_samples_per_second": 96.95,
|
| 608 |
"eval_steps_per_second": 6.06,
|
| 609 |
"step": 40000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 43.29,
|
| 613 |
+
"learning_rate": 1.583949313621964e-05,
|
| 614 |
+
"loss": 0.2516,
|
| 615 |
+
"step": 41000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 43.29,
|
| 619 |
+
"eval_accuracy": 0.9011221122112211,
|
| 620 |
+
"eval_loss": 0.39773184061050415,
|
| 621 |
+
"eval_runtime": 155.7863,
|
| 622 |
+
"eval_samples_per_second": 97.249,
|
| 623 |
+
"eval_steps_per_second": 6.079,
|
| 624 |
+
"step": 41000
|
| 625 |
}
|
| 626 |
],
|
| 627 |
"logging_steps": 1000,
|
|
|
|
| 629 |
"num_input_tokens_seen": 0,
|
| 630 |
"num_train_epochs": 500,
|
| 631 |
"save_steps": 1000,
|
| 632 |
+
"total_flos": 2.0349272368495054e+20,
|
| 633 |
"train_batch_size": 16,
|
| 634 |
"trial_name": null,
|
| 635 |
"trial_params": null
|