Shresthadev403 commited on
Commit
c24edf6
1 Parent(s): 0a122c1

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: 0.3627
19
- - eval_accuracy: 0.9083
20
- - eval_runtime: 156.6773
21
- - eval_samples_per_second: 96.696
22
- - eval_steps_per_second: 6.044
23
- - epoch: 32.73
24
- - step: 31000
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: 0.3558
19
+ - eval_accuracy: 0.9109
20
+ - eval_runtime: 155.255
21
+ - eval_samples_per_second: 97.581
22
+ - eval_steps_per_second: 6.1
23
+ - epoch: 33.79
24
+ - step: 32000
25
 
26
  ## Model description
27
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:874919a86cf76f4c4fd89a105e0315431501974a85a4da8f592237386746e315
3
  size 343528508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2363016a1361f2c999852e918a415cf33ecbfcc46a9ec24145333c05eca341c6
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 sha256:6b495246ccb3b8bbfa902382acd6ac8b909fe3278bdea3b1773569bc8f6da22f
3
- size 11848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab0af5591e1785017879a9ecc581490454f295c99aba4ac55ab1496e890c14f
3
+ size 12337
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.9113531353135313,
3
  "best_model_checkpoint": "food-image-classification/checkpoint-28000",
4
- "epoch": 32.734952481520594,
5
  "eval_steps": 1000,
6
- "global_step": 31000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -472,6 +472,21 @@
472
  "eval_samples_per_second": 96.696,
473
  "eval_steps_per_second": 6.044,
474
  "step": 31000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
475
  }
476
  ],
477
  "logging_steps": 1000,
@@ -479,7 +494,7 @@
479
  "num_input_tokens_seen": 0,
480
  "num_train_epochs": 500,
481
  "save_steps": 1000,
482
- "total_flos": 1.538606698643718e+20,
483
  "train_batch_size": 16,
484
  "trial_name": null,
485
  "trial_params": null
 
1
  {
2
  "best_metric": 0.9113531353135313,
3
  "best_model_checkpoint": "food-image-classification/checkpoint-28000",
4
+ "epoch": 33.7909186906019,
5
  "eval_steps": 1000,
6
+ "global_step": 32000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
472
  "eval_samples_per_second": 96.696,
473
  "eval_steps_per_second": 6.044,
474
  "step": 31000
475
+ },
476
+ {
477
+ "epoch": 33.79,
478
+ "learning_rate": 6.335797254487856e-06,
479
+ "loss": 0.3189,
480
+ "step": 32000
481
+ },
482
+ {
483
+ "epoch": 33.79,
484
+ "eval_accuracy": 0.9108910891089109,
485
+ "eval_loss": 0.35579344630241394,
486
+ "eval_runtime": 155.255,
487
+ "eval_samples_per_second": 97.581,
488
+ "eval_steps_per_second": 6.1,
489
+ "step": 32000
490
  }
491
  ],
492
  "logging_steps": 1000,
 
494
  "num_input_tokens_seen": 0,
495
  "num_train_epochs": 500,
496
  "save_steps": 1000,
497
+ "total_flos": 1.5882393729502865e+20,
498
  "train_batch_size": 16,
499
  "trial_name": null,
500
  "trial_params": null