Eliott Z commited on
Commit
6c3a949
1 Parent(s): c1c6ef2

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 3.434605836868286,
4
+ "eval_runtime": 27.4805,
5
+ "eval_samples": 5770,
6
+ "eval_samples_per_second": 209.967,
7
+ "eval_steps_per_second": 13.137,
8
+ "train_loss": 3.8245478040389433,
9
+ "train_runtime": 4489.0093,
10
+ "train_samples": 58681,
11
+ "train_samples_per_second": 13.072,
12
+ "train_steps_per_second": 0.817
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 3.434605836868286,
4
+ "eval_runtime": 27.4805,
5
+ "eval_samples": 5770,
6
+ "eval_samples_per_second": 209.967,
7
+ "eval_steps_per_second": 13.137
8
+ }
runs/Jul18_16-35-58_sauron-preemptible/events.out.tfevents.1658166885.sauron-preemptible.3188.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a125c78a049a46c91d3329721271c4f6595584f447138967d7c3e0eea9bc971d
3
+ size 311
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 3.8245478040389433,
4
+ "train_runtime": 4489.0093,
5
+ "train_samples": 58681,
6
+ "train_samples_per_second": 13.072,
7
+ "train_steps_per_second": 0.817
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 3668,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.14,
12
+ "learning_rate": 9.134948096885815e-06,
13
+ "loss": 4.3058,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.27,
18
+ "learning_rate": 7.693194925028837e-06,
19
+ "loss": 3.8423,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "eval_loss": 3.5093352794647217,
25
+ "eval_runtime": 26.1408,
26
+ "eval_samples_per_second": 220.728,
27
+ "eval_steps_per_second": 13.81,
28
+ "step": 1000
29
+ },
30
+ {
31
+ "epoch": 0.41,
32
+ "learning_rate": 6.251441753171857e-06,
33
+ "loss": 3.7858,
34
+ "step": 1500
35
+ },
36
+ {
37
+ "epoch": 0.55,
38
+ "learning_rate": 4.809688581314879e-06,
39
+ "loss": 3.7475,
40
+ "step": 2000
41
+ },
42
+ {
43
+ "epoch": 0.55,
44
+ "eval_loss": 3.46193265914917,
45
+ "eval_runtime": 26.4806,
46
+ "eval_samples_per_second": 217.896,
47
+ "eval_steps_per_second": 13.633,
48
+ "step": 2000
49
+ },
50
+ {
51
+ "epoch": 0.68,
52
+ "learning_rate": 3.367935409457901e-06,
53
+ "loss": 3.7268,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 0.82,
58
+ "learning_rate": 1.926182237600923e-06,
59
+ "loss": 3.7098,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 0.82,
64
+ "eval_loss": 3.436793327331543,
65
+ "eval_runtime": 26.5912,
66
+ "eval_samples_per_second": 216.989,
67
+ "eval_steps_per_second": 13.576,
68
+ "step": 3000
69
+ },
70
+ {
71
+ "epoch": 0.95,
72
+ "learning_rate": 4.844290657439446e-07,
73
+ "loss": 3.6983,
74
+ "step": 3500
75
+ },
76
+ {
77
+ "epoch": 1.0,
78
+ "step": 3668,
79
+ "total_flos": 733768405493760.0,
80
+ "train_loss": 3.8245478040389433,
81
+ "train_runtime": 4489.0093,
82
+ "train_samples_per_second": 13.072,
83
+ "train_steps_per_second": 0.817
84
+ }
85
+ ],
86
+ "max_steps": 3668,
87
+ "num_train_epochs": 1,
88
+ "total_flos": 733768405493760.0,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }