amyeroberts HF staff commited on
Commit
15a23f5
1 Parent(s): ed1e87e

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 5474.208984375,
4
+ "eval_runtime": 2.3559,
5
+ "eval_samples_per_second": 13.583,
6
+ "eval_steps_per_second": 1.698,
7
+ "train_loss": 4986.834765625,
8
+ "train_runtime": 89.7426,
9
+ "train_samples_per_second": 1.783,
10
+ "train_steps_per_second": 0.223
11
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 5474.208984375,
4
+ "eval_runtime": 2.3559,
5
+ "eval_samples_per_second": 13.583,
6
+ "eval_steps_per_second": 1.698
7
+ }
runs/Jul18_19-13-43_amy-2-gpu/events.out.tfevents.1689707738.amy-2-gpu.31153.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af1e091c334c0dfc392cd5a266eb429320e2131dcdfe2cc2f755b3db25671126
3
+ size 354
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 4986.834765625,
4
+ "train_runtime": 89.7426,
5
+ "train_samples_per_second": 1.783,
6
+ "train_steps_per_second": 0.223
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 5474.208984375,
3
+ "best_model_checkpoint": "./coco_outputs/checkpoint-20",
4
+ "epoch": 5.0,
5
+ "global_step": 20,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_loss": 5475.6171875,
13
+ "eval_runtime": 2.202,
14
+ "eval_samples_per_second": 14.532,
15
+ "eval_steps_per_second": 1.816,
16
+ "step": 4
17
+ },
18
+ {
19
+ "epoch": 2.0,
20
+ "eval_loss": 5475.1103515625,
21
+ "eval_runtime": 2.2765,
22
+ "eval_samples_per_second": 14.056,
23
+ "eval_steps_per_second": 1.757,
24
+ "step": 8
25
+ },
26
+ {
27
+ "epoch": 2.5,
28
+ "learning_rate": 1e-05,
29
+ "loss": 4957.6352,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_loss": 5474.685546875,
35
+ "eval_runtime": 2.2499,
36
+ "eval_samples_per_second": 14.223,
37
+ "eval_steps_per_second": 1.778,
38
+ "step": 12
39
+ },
40
+ {
41
+ "epoch": 4.0,
42
+ "eval_loss": 5474.34375,
43
+ "eval_runtime": 2.2284,
44
+ "eval_samples_per_second": 14.36,
45
+ "eval_steps_per_second": 1.795,
46
+ "step": 16
47
+ },
48
+ {
49
+ "epoch": 5.0,
50
+ "learning_rate": 0.0,
51
+ "loss": 5016.0344,
52
+ "step": 20
53
+ },
54
+ {
55
+ "epoch": 5.0,
56
+ "eval_loss": 5474.208984375,
57
+ "eval_runtime": 2.3127,
58
+ "eval_samples_per_second": 13.837,
59
+ "eval_steps_per_second": 1.73,
60
+ "step": 20
61
+ },
62
+ {
63
+ "epoch": 5.0,
64
+ "step": 20,
65
+ "total_flos": 7.65002115072e+16,
66
+ "train_loss": 4986.834765625,
67
+ "train_runtime": 89.7426,
68
+ "train_samples_per_second": 1.783,
69
+ "train_steps_per_second": 0.223
70
+ }
71
+ ],
72
+ "max_steps": 20,
73
+ "num_train_epochs": 5,
74
+ "total_flos": 7.65002115072e+16,
75
+ "trial_name": null,
76
+ "trial_params": null
77
+ }