aee4 commited on
Commit
01a6631
·
verified ·
1 Parent(s): 069f790

Training in progress, step 250, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AMFUNet"
4
+ ],
5
+ "base_channels": 32,
6
+ "dtype": "float32",
7
+ "image_size": 256,
8
+ "model_type": "amfu-net",
9
+ "transformers_version": "4.57.1"
10
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78880a3693746bf5152ab29a120d2a290eee09cccafcce6dae47931c80b246ce
3
+ size 76153420
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59eb0fca452e9ba14aa43517fcbf06e40f8ba447160155035580017c8db5d748
3
+ size 152327371
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2780207a4d14a0d6ae72f4e5a69d10a3b1857d431b48bab7a7ca29d13564a6fe
3
+ size 1465
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 250,
3
+ "best_metric": 0.5238277956707055,
4
+ "best_model_checkpoint": "/kaggle/working/G17_amfu_paper_training/trainer_output/checkpoint-250",
5
+ "epoch": 1.4124293785310735,
6
+ "eval_steps": 250,
7
+ "global_step": 250,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.14124293785310735,
14
+ "grad_norm": 0.8879454135894775,
15
+ "learning_rate": 0.001,
16
+ "loss": 1.4777,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.2824858757062147,
21
+ "grad_norm": 0.967484712600708,
22
+ "learning_rate": 0.001,
23
+ "loss": 1.3083,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.423728813559322,
28
+ "grad_norm": 0.6732232570648193,
29
+ "learning_rate": 0.001,
30
+ "loss": 1.197,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.5649717514124294,
35
+ "grad_norm": 0.7241559624671936,
36
+ "learning_rate": 0.001,
37
+ "loss": 1.0729,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.7062146892655368,
42
+ "grad_norm": 2.5539605617523193,
43
+ "learning_rate": 0.001,
44
+ "loss": 1.0002,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.847457627118644,
49
+ "grad_norm": 0.7198242545127869,
50
+ "learning_rate": 0.001,
51
+ "loss": 0.9364,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.9887005649717514,
56
+ "grad_norm": 0.8868919014930725,
57
+ "learning_rate": 0.001,
58
+ "loss": 0.849,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 1.1299435028248588,
63
+ "grad_norm": 1.1395323276519775,
64
+ "learning_rate": 0.001,
65
+ "loss": 0.8297,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 1.271186440677966,
70
+ "grad_norm": 1.0387303829193115,
71
+ "learning_rate": 0.001,
72
+ "loss": 0.7734,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 1.4124293785310735,
77
+ "grad_norm": 1.1483888626098633,
78
+ "learning_rate": 0.001,
79
+ "loss": 0.7389,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 1.4124293785310735,
84
+ "eval_asd": 38.593632422634066,
85
+ "eval_dice": 0.5238277956707055,
86
+ "eval_hd95": 104.37561289160895,
87
+ "eval_jaccard": 0.3899429974682844,
88
+ "eval_loss": 0.8055315613746643,
89
+ "eval_runtime": 5.1009,
90
+ "eval_samples_per_second": 50.971,
91
+ "eval_steps_per_second": 12.743,
92
+ "step": 250
93
+ }
94
+ ],
95
+ "logging_steps": 25,
96
+ "max_steps": 35400,
97
+ "num_input_tokens_seen": 0,
98
+ "num_train_epochs": 200,
99
+ "save_steps": 250,
100
+ "stateful_callbacks": {
101
+ "TrainerControl": {
102
+ "args": {
103
+ "should_epoch_stop": false,
104
+ "should_evaluate": false,
105
+ "should_log": false,
106
+ "should_save": true,
107
+ "should_training_stop": false
108
+ },
109
+ "attributes": {}
110
+ }
111
+ },
112
+ "total_flos": 0.0,
113
+ "train_batch_size": 4,
114
+ "trial_name": null,
115
+ "trial_params": null
116
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf3f58db0994b999d0d602990a55c5c92a50d6e23724d47cb41b0cdcfa03e760
3
+ size 5905