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: 0.3803
|
| 19 |
+
- eval_accuracy: 0.9053
|
| 20 |
+
- eval_runtime: 154.4972
|
| 21 |
+
- eval_samples_per_second: 98.06
|
| 22 |
+
- eval_steps_per_second: 6.13
|
| 23 |
+
- epoch: 41.18
|
| 24 |
+
- step: 39000
|
| 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 sha256:30786e54b7d48e926b336090be2d66a0cca9bb587868dcb76051b0eb87ab0ab1
|
| 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:e44a2a7173ba554c9bdcba047abceb12d0a7113e90092fe3b90ab5fae5bc0531
|
| 3 |
+
size 15760
|
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,
|
|
@@ -577,6 +577,21 @@
|
|
| 577 |
"eval_samples_per_second": 97.627,
|
| 578 |
"eval_steps_per_second": 6.103,
|
| 579 |
"step": 38000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 580 |
}
|
| 581 |
],
|
| 582 |
"logging_steps": 1000,
|
|
@@ -584,7 +599,7 @@
|
|
| 584 |
"num_input_tokens_seen": 0,
|
| 585 |
"num_train_epochs": 500,
|
| 586 |
"save_steps": 1000,
|
| 587 |
-
"total_flos": 1.
|
| 588 |
"train_batch_size": 16,
|
| 589 |
"trial_name": null,
|
| 590 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9115511551155115,
|
| 3 |
"best_model_checkpoint": "food-image-classification/checkpoint-35000",
|
| 4 |
+
"epoch": 41.18268215417107,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 39000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 577 |
"eval_samples_per_second": 97.627,
|
| 578 |
"eval_steps_per_second": 6.103,
|
| 579 |
"step": 38000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 41.18,
|
| 583 |
+
"learning_rate": 1.3727560718057022e-05,
|
| 584 |
+
"loss": 0.2585,
|
| 585 |
+
"step": 39000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 41.18,
|
| 589 |
+
"eval_accuracy": 0.9052805280528052,
|
| 590 |
+
"eval_loss": 0.3803286850452423,
|
| 591 |
+
"eval_runtime": 154.4972,
|
| 592 |
+
"eval_samples_per_second": 98.06,
|
| 593 |
+
"eval_steps_per_second": 6.13,
|
| 594 |
+
"step": 39000
|
| 595 |
}
|
| 596 |
],
|
| 597 |
"logging_steps": 1000,
|
|
|
|
| 599 |
"num_input_tokens_seen": 0,
|
| 600 |
"num_train_epochs": 500,
|
| 601 |
"save_steps": 1000,
|
| 602 |
+
"total_flos": 1.9356618882363687e+20,
|
| 603 |
"train_batch_size": 16,
|
| 604 |
"trial_name": null,
|
| 605 |
"trial_params": null
|