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: 0.4645
|
| 19 |
+
- eval_accuracy: 0.8831
|
| 20 |
+
- eval_runtime: 156.6057
|
| 21 |
+
- eval_samples_per_second: 96.74
|
| 22 |
+
- eval_steps_per_second: 6.047
|
| 23 |
+
- epoch: 54.91
|
| 24 |
+
- step: 52000
|
| 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 sha256:3f8614863907fd855c9a68363be9a5137138b24c5d0e895d7639375b16d6a6bb
|
| 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 sha256:860ab5fcd4edbfa73249c65e42696f79dfbc19e6121cc783d0e0717087ddf76c
|
| 3 |
+
size 22117
|
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,
|
|
@@ -772,6 +772,21 @@
|
|
| 772 |
"eval_samples_per_second": 97.344,
|
| 773 |
"eval_steps_per_second": 6.085,
|
| 774 |
"step": 51000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 775 |
}
|
| 776 |
],
|
| 777 |
"logging_steps": 1000,
|
|
@@ -779,7 +794,7 @@
|
|
| 779 |
"num_input_tokens_seen": 0,
|
| 780 |
"num_train_epochs": 500,
|
| 781 |
"save_steps": 1000,
|
| 782 |
-
"total_flos": 2.
|
| 783 |
"train_batch_size": 16,
|
| 784 |
"trial_name": null,
|
| 785 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9115511551155115,
|
| 3 |
"best_model_checkpoint": "food-image-classification/checkpoint-35000",
|
| 4 |
+
"epoch": 54.91024287222809,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 52000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 772 |
"eval_samples_per_second": 97.344,
|
| 773 |
"eval_steps_per_second": 6.085,
|
| 774 |
"step": 51000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 54.91,
|
| 778 |
+
"learning_rate": 2.7455121436114044e-05,
|
| 779 |
+
"loss": 0.2164,
|
| 780 |
+
"step": 52000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 54.91,
|
| 784 |
+
"eval_accuracy": 0.8831023102310231,
|
| 785 |
+
"eval_loss": 0.4645076394081116,
|
| 786 |
+
"eval_runtime": 156.6057,
|
| 787 |
+
"eval_samples_per_second": 96.74,
|
| 788 |
+
"eval_steps_per_second": 6.047,
|
| 789 |
+
"step": 52000
|
| 790 |
}
|
| 791 |
],
|
| 792 |
"logging_steps": 1000,
|
|
|
|
| 794 |
"num_input_tokens_seen": 0,
|
| 795 |
"num_train_epochs": 500,
|
| 796 |
"save_steps": 1000,
|
| 797 |
+
"total_flos": 2.5808866542217573e+20,
|
| 798 |
"train_batch_size": 16,
|
| 799 |
"trial_name": null,
|
| 800 |
"trial_params": null
|