Hugging Face's logo

harisali9211
/
trocr-large-printed-e13b_tesseract_MICR_ocr

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Model card Files Metrics Community
harisali9211 commited on
Commit
fcd9930
·
verified ·
1 Parent(s): e918ed6

All Dunn!!!

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +95 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 7.193998576047882e+17,
4
+ "train_loss": 1.5048968147058956,
5
+ "train_runtime": 791.7321,
6
+ "train_samples_per_second": 0.614,
7
+ "train_steps_per_second": 0.154
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 7.193998576047882e+17,
4
+ "train_loss": 1.5048968147058956,
5
+ "train_runtime": 791.7321,
6
+ "train_samples_per_second": 0.614,
7
+ "train_steps_per_second": 0.154
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 122,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01639344262295082,
13
+ "grad_norm": 178.06546020507812,
14
+ "learning_rate": 4.959016393442623e-05,
15
+ "loss": 8.943,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.47540983606557374,
20
+ "grad_norm": 54.69188690185547,
21
+ "learning_rate": 3.8114754098360655e-05,
22
+ "loss": 2.2897,
23
+ "step": 29
24
+ },
25
+ {
26
+ "epoch": 0.9508196721311475,
27
+ "grad_norm": 16.769203186035156,
28
+ "learning_rate": 2.6229508196721314e-05,
29
+ "loss": 2.0108,
30
+ "step": 58
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "eval_cer": 0.1530448717948718,
35
+ "eval_loss": 1.128391981124878,
36
+ "eval_runtime": 125.6559,
37
+ "eval_samples_per_second": 0.485,
38
+ "eval_steps_per_second": 0.064,
39
+ "step": 61
40
+ },
41
+ {
42
+ "epoch": 1.4262295081967213,
43
+ "grad_norm": 30.61115837097168,
44
+ "learning_rate": 1.4344262295081968e-05,
45
+ "loss": 1.1471,
46
+ "step": 87
47
+ },
48
+ {
49
+ "epoch": 1.901639344262295,
50
+ "grad_norm": 10.20889663696289,
51
+ "learning_rate": 2.459016393442623e-06,
52
+ "loss": 0.5665,
53
+ "step": 116
54
+ },
55
+ {
56
+ "epoch": 2.0,
57
+ "eval_cer": 0.03125,
58
+ "eval_loss": 0.5153284072875977,
59
+ "eval_runtime": 107.7401,
60
+ "eval_samples_per_second": 0.566,
61
+ "eval_steps_per_second": 0.074,
62
+ "step": 122
63
+ },
64
+ {
65
+ "epoch": 2.0,
66
+ "step": 122,
67
+ "total_flos": 7.193998576047882e+17,
68
+ "train_loss": 1.5048968147058956,
69
+ "train_runtime": 791.7321,
70
+ "train_samples_per_second": 0.614,
71
+ "train_steps_per_second": 0.154
72
+ }
73
+ ],
74
+ "logging_steps": 29,
75
+ "max_steps": 122,
76
+ "num_input_tokens_seen": 0,
77
+ "num_train_epochs": 2,
78
+ "save_steps": 500,
79
+ "stateful_callbacks": {
80
+ "TrainerControl": {
81
+ "args": {
82
+ "should_epoch_stop": false,
83
+ "should_evaluate": false,
84
+ "should_log": false,
85
+ "should_save": true,
86
+ "should_training_stop": true
87
+ },
88
+ "attributes": {}
89
+ }
90
+ },
91
+ "total_flos": 7.193998576047882e+17,
92
+ "train_batch_size": 4,
93
+ "trial_name": null,
94
+ "trial_params": null
95
+ }