Hugging Face's logo

CVPROJ25
/
FINETUNED

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Model card Files
xet
 Community
hanngao commited on
Commit
9cbdd96
·
verified ·
1 Parent(s): 2ace48b

Training in progress, epoch 1, checkpoint

Browse files
Files changed (2) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/trainer_state.json +13 -52
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:994af4ef7e2e21f7bab319c9006c4111aceb192de8105891aa574e895d2c3eef
3
  size 346293856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c813c0dbd822da8514932dbbec01648b0256caad1eac079b51d006ea985af7a0
3
  size 346293856
last-checkpoint/trainer_state.json CHANGED
@@ -1,68 +1,29 @@
1
  {
2
  "best_global_step": 16,
3
- "best_metric": 0.8204972743988037,
4
  "best_model_checkpoint": "./finetuning/checkpoint-16",
5
- "epoch": 3.0,
6
  "eval_steps": 500,
7
- "global_step": 48,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
  "epoch": 0.625,
14
- "grad_norm": 2.155005931854248,
15
  "learning_rate": 4.71875e-05,
16
- "loss": 0.7260067462921143,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 1.0,
21
- "eval_accuracy": 0.789,
22
- "eval_loss": 0.8204972743988037,
23
- "eval_runtime": 101.3291,
24
- "eval_samples_per_second": 19.738,
25
- "eval_steps_per_second": 1.234,
26
  "step": 16
27
- },
28
- {
29
- "epoch": 1.25,
30
- "grad_norm": 1.2275031805038452,
31
- "learning_rate": 4.40625e-05,
32
- "loss": 0.5976850986480713,
33
- "step": 20
34
- },
35
- {
36
- "epoch": 1.875,
37
- "grad_norm": 1.2741576433181763,
38
- "learning_rate": 4.09375e-05,
39
- "loss": 0.36108148097991943,
40
- "step": 30
41
- },
42
- {
43
- "epoch": 2.0,
44
- "eval_accuracy": 0.784,
45
- "eval_loss": 0.837196409702301,
46
- "eval_runtime": 98.979,
47
- "eval_samples_per_second": 20.206,
48
- "eval_steps_per_second": 1.263,
49
- "step": 32
50
- },
51
- {
52
- "epoch": 2.5,
53
- "grad_norm": 0.7750149965286255,
54
- "learning_rate": 3.78125e-05,
55
- "loss": 0.25730888843536376,
56
- "step": 40
57
- },
58
- {
59
- "epoch": 3.0,
60
- "eval_accuracy": 0.785,
61
- "eval_loss": 0.8522552847862244,
62
- "eval_runtime": 98.5747,
63
- "eval_samples_per_second": 20.289,
64
- "eval_steps_per_second": 1.268,
65
- "step": 48
66
  }
67
  ],
68
  "logging_steps": 10,
@@ -77,7 +38,7 @@
77
  "early_stopping_threshold": 0.0
78
  },
79
  "attributes": {
80
- "early_stopping_patience_counter": 2
81
  }
82
  },
83
  "TrainerControl": {
@@ -86,12 +47,12 @@
86
  "should_evaluate": false,
87
  "should_log": false,
88
  "should_save": true,
89
- "should_training_stop": true
90
  },
91
  "attributes": {}
92
  }
93
  },
94
- "total_flos": 1.876443281620992e+18,
95
  "train_batch_size": 512,
96
  "trial_name": null,
97
  "trial_params": null
 
1
  {
2
  "best_global_step": 16,
3
+ "best_metric": 0.8921805620193481,
4
  "best_model_checkpoint": "./finetuning/checkpoint-16",
5
+ "epoch": 1.0,
6
  "eval_steps": 500,
7
+ "global_step": 16,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
  "epoch": 0.625,
14
+ "grad_norm": 2.303117513656616,
15
  "learning_rate": 4.71875e-05,
16
+ "loss": 0.8241110801696777,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 1.0,
21
+ "eval_accuracy": 0.773,
22
+ "eval_loss": 0.8921805620193481,
23
+ "eval_runtime": 108.5097,
24
+ "eval_samples_per_second": 18.432,
25
+ "eval_steps_per_second": 1.152,
26
  "step": 16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  }
28
  ],
29
  "logging_steps": 10,
 
38
  "early_stopping_threshold": 0.0
39
  },
40
  "attributes": {
41
+ "early_stopping_patience_counter": 0
42
  }
43
  },
44
  "TrainerControl": {
 
47
  "should_evaluate": false,
48
  "should_log": false,
49
  "should_save": true,
50
+ "should_training_stop": false
51
  },
52
  "attributes": {}
53
  }
54
  },
55
+ "total_flos": 6.25481093873664e+17,
56
  "train_batch_size": 512,
57
  "trial_name": null,
58
  "trial_params": null