Hugging Face's logo

CVPROJ25
/
FINETUNED

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Model card Files
xet
 Community
hanngao commited on
Commit
be4a91e
·
verified ·
1 Parent(s): 9c38d47

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 +15 -77
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf7985d8f4dde4ad05e6f6b9a19451dc06a0c1e2f9441d05e6209497768a4d0
3
  size 346293856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4463b5d2a15f49e3fe254d29ac15a3013e09f79a1aa45554a48914c5dd438748
3
  size 346293856
last-checkpoint/trainer_state.json CHANGED
@@ -1,91 +1,29 @@
1
  {
2
- "best_global_step": 32,
3
- "best_metric": 1.1040924787521362,
4
- "best_model_checkpoint": "./finetuning/checkpoint-32",
5
- "epoch": 4.0,
6
  "eval_steps": 500,
7
- "global_step": 64,
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": 2.930115222930908,
15
  "learning_rate": 4.71875e-05,
16
- "loss": 1.1392939567565918,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 1.0,
21
- "eval_accuracy": 0.7265,
22
- "eval_loss": 1.1167327165603638,
23
- "eval_runtime": 99.6317,
24
- "eval_samples_per_second": 20.074,
25
- "eval_steps_per_second": 1.255,
26
  "step": 16
27
- },
28
- {
29
- "epoch": 1.25,
30
- "grad_norm": 1.9330124855041504,
31
- "learning_rate": 4.40625e-05,
32
- "loss": 0.8287152290344239,
33
- "step": 20
34
- },
35
- {
36
- "epoch": 1.875,
37
- "grad_norm": 1.747740387916565,
38
- "learning_rate": 4.09375e-05,
39
- "loss": 0.5591425418853759,
40
- "step": 30
41
- },
42
- {
43
- "epoch": 2.0,
44
- "eval_accuracy": 0.7345,
45
- "eval_loss": 1.1040924787521362,
46
- "eval_runtime": 98.3532,
47
- "eval_samples_per_second": 20.335,
48
- "eval_steps_per_second": 1.271,
49
- "step": 32
50
- },
51
- {
52
- "epoch": 2.5,
53
- "grad_norm": 1.1616895198822021,
54
- "learning_rate": 3.78125e-05,
55
- "loss": 0.40230541229248046,
56
- "step": 40
57
- },
58
- {
59
- "epoch": 3.0,
60
- "eval_accuracy": 0.7315,
61
- "eval_loss": 1.1306830644607544,
62
- "eval_runtime": 98.0319,
63
- "eval_samples_per_second": 20.402,
64
- "eval_steps_per_second": 1.275,
65
- "step": 48
66
- },
67
- {
68
- "epoch": 3.125,
69
- "grad_norm": 0.9498137831687927,
70
- "learning_rate": 3.46875e-05,
71
- "loss": 0.30755977630615233,
72
- "step": 50
73
- },
74
- {
75
- "epoch": 3.75,
76
- "grad_norm": 0.7574973702430725,
77
- "learning_rate": 3.15625e-05,
78
- "loss": 0.21216330528259278,
79
- "step": 60
80
- },
81
- {
82
- "epoch": 4.0,
83
- "eval_accuracy": 0.7235,
84
- "eval_loss": 1.1593739986419678,
85
- "eval_runtime": 100.5022,
86
- "eval_samples_per_second": 19.9,
87
- "eval_steps_per_second": 1.244,
88
- "step": 64
89
  }
90
  ],
91
  "logging_steps": 10,
@@ -100,7 +38,7 @@
100
  "early_stopping_threshold": 0.0
101
  },
102
  "attributes": {
103
- "early_stopping_patience_counter": 2
104
  }
105
  },
106
  "TrainerControl": {
@@ -109,12 +47,12 @@
109
  "should_evaluate": false,
110
  "should_log": false,
111
  "should_save": true,
112
- "should_training_stop": true
113
  },
114
  "attributes": {}
115
  }
116
  },
117
- "total_flos": 2.501924375494656e+18,
118
  "train_batch_size": 512,
119
  "trial_name": null,
120
  "trial_params": null
 
1
  {
2
+ "best_global_step": 16,
3
+ "best_metric": 0.8204972743988037,
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": 2.155005931854248,
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
  "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