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: 0.4482
|
| 19 |
+
- eval_accuracy: 0.8876
|
| 20 |
+
- eval_runtime: 155.8513
|
| 21 |
+
- eval_samples_per_second: 97.208
|
| 22 |
+
- eval_steps_per_second: 6.076
|
| 23 |
+
- epoch: 50.69
|
| 24 |
+
- step: 48000
|
| 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 sha256:4374a321cd293ea774254fa25ea760a058020efb6344c188a6998c3a37fcff42
|
| 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 sha256:150d9961573e1c0fa6611dfa44b33bf5d99d33a32880f1b9f140f0e9e1e961fe
|
| 3 |
+
size 20161
|
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,
|
|
@@ -712,6 +712,21 @@
|
|
| 712 |
"eval_samples_per_second": 96.791,
|
| 713 |
"eval_steps_per_second": 6.05,
|
| 714 |
"step": 47000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 715 |
}
|
| 716 |
],
|
| 717 |
"logging_steps": 1000,
|
|
@@ -719,7 +734,7 @@
|
|
| 719 |
"num_input_tokens_seen": 0,
|
| 720 |
"num_train_epochs": 500,
|
| 721 |
"save_steps": 1000,
|
| 722 |
-
"total_flos": 2.
|
| 723 |
"train_batch_size": 16,
|
| 724 |
"trial_name": null,
|
| 725 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9115511551155115,
|
| 3 |
"best_model_checkpoint": "food-image-classification/checkpoint-35000",
|
| 4 |
+
"epoch": 50.68637803590285,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 48000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 712 |
"eval_samples_per_second": 96.791,
|
| 713 |
"eval_steps_per_second": 6.05,
|
| 714 |
"step": 47000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 50.69,
|
| 718 |
+
"learning_rate": 2.323125659978881e-05,
|
| 719 |
+
"loss": 0.2247,
|
| 720 |
+
"step": 48000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 50.69,
|
| 724 |
+
"eval_accuracy": 0.8875907590759076,
|
| 725 |
+
"eval_loss": 0.4481562674045563,
|
| 726 |
+
"eval_runtime": 155.8513,
|
| 727 |
+
"eval_samples_per_second": 97.208,
|
| 728 |
+
"eval_steps_per_second": 6.076,
|
| 729 |
+
"step": 48000
|
| 730 |
}
|
| 731 |
],
|
| 732 |
"logging_steps": 1000,
|
|
|
|
| 734 |
"num_input_tokens_seen": 0,
|
| 735 |
"num_train_epochs": 500,
|
| 736 |
"save_steps": 1000,
|
| 737 |
+
"total_flos": 2.382355956995484e+20,
|
| 738 |
"train_batch_size": 16,
|
| 739 |
"trial_name": null,
|
| 740 |
"trial_params": null
|