Hugging Face's logo

merve
/
kosmos-2.5-ft

Image-Text-to-Text
Transformers
Safetensors
kosmos-2.5
ocr
Model card Files
xet
Community
merve HF Staff commited on
Commit
e8ca3dc
·
verified ·
1 Parent(s): 5a3285a

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +111 -0
trainer_state.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1126,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.17777777777777778,
14
+ "grad_norm": 1.1875,
15
+ "learning_rate": 1.827402135231317e-05,
16
+ "loss": 0.4486,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.35555555555555557,
21
+ "grad_norm": 1.21875,
22
+ "learning_rate": 1.6494661921708185e-05,
23
+ "loss": 0.1052,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.5333333333333333,
28
+ "grad_norm": 0.90625,
29
+ "learning_rate": 1.4715302491103204e-05,
30
+ "loss": 0.0932,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.7111111111111111,
35
+ "grad_norm": 1.3984375,
36
+ "learning_rate": 1.2935943060498222e-05,
37
+ "loss": 0.0988,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.8888888888888888,
42
+ "grad_norm": 1.5703125,
43
+ "learning_rate": 1.1156583629893238e-05,
44
+ "loss": 0.0903,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 1.0657777777777777,
49
+ "grad_norm": 1.265625,
50
+ "learning_rate": 9.377224199288258e-06,
51
+ "loss": 0.0912,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 1.2435555555555555,
56
+ "grad_norm": 0.65234375,
57
+ "learning_rate": 7.597864768683275e-06,
58
+ "loss": 0.0798,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 1.4213333333333333,
63
+ "grad_norm": 1.890625,
64
+ "learning_rate": 5.818505338078292e-06,
65
+ "loss": 0.0835,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 1.5991111111111111,
70
+ "grad_norm": 2.015625,
71
+ "learning_rate": 4.03914590747331e-06,
72
+ "loss": 0.0785,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 1.7768888888888887,
77
+ "grad_norm": 1.546875,
78
+ "learning_rate": 2.2597864768683274e-06,
79
+ "loss": 0.0785,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 1.9546666666666668,
84
+ "grad_norm": 2.15625,
85
+ "learning_rate": 4.804270462633452e-07,
86
+ "loss": 0.079,
87
+ "step": 1100
88
+ }
89
+ ],
90
+ "logging_steps": 100,
91
+ "max_steps": 1126,
92
+ "num_input_tokens_seen": 0,
93
+ "num_train_epochs": 2,
94
+ "save_steps": 1000,
95
+ "stateful_callbacks": {
96
+ "TrainerControl": {
97
+ "args": {
98
+ "should_epoch_stop": false,
99
+ "should_evaluate": false,
100
+ "should_log": false,
101
+ "should_save": true,
102
+ "should_training_stop": true
103
+ },
104
+ "attributes": {}
105
+ }
106
+ },
107
+ "total_flos": 1.1068310033650483e+17,
108
+ "train_batch_size": 1,
109
+ "trial_name": null,
110
+ "trial_params": null
111
+ }