meghana commited on
Commit
ade6df8
1 Parent(s): 992a6b0

End of training

Browse files
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2617113b2f749bfc5e4ea1ee6332364f083816929cbf0920fc509e86767b8235
3
+ size 4470971045
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95b53233a130e0e8107abf19d44dd483ffb59cf3ecb78e9385adb6df1e118d57
3
  size 2235534897
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56d48178cde0e4b32dd5d267dd2397a64bd41e0217efefb1963143360bfe81e
3
  size 2235534897
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbd13d01445b4f1746dd83c783270789807899976916ab406fcb2ddb8cc6591
3
+ size 14503
runs/Oct19_13-53-11_59dbd650438a/1634660101.8097117/events.out.tfevents.1634660101.59dbd650438a.92.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f40738dff53fa7cd3c0f5cbfd4a896d0132382557c4f862eab913b447b0a620
3
+ size 4531
runs/Oct19_13-53-11_59dbd650438a/events.out.tfevents.1634651610.59dbd650438a.92.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ba9dfb5495d031a4e7177757e8a8e6cf3c5f9c8c7c33c998f9a6e8fab077ab0
3
- size 3367
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e6386a433e314eb15e4bdb5e700785d9632316f92df847e0d2dac1646fc656
3
+ size 9671
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb426f91a2308e1f72b620b9420014ac1c498eaa6f7e1b0e3344a77e80aa672
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.7100513015390462,
5
+ "global_step": 9000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 1.936664766609665e-05,
13
+ "loss": 0.9425,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.19,
18
+ "learning_rate": 1.87332953321933e-05,
19
+ "loss": 0.8195,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.29,
24
+ "learning_rate": 1.809994299828995e-05,
25
+ "loss": 0.65,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.38,
30
+ "learning_rate": 1.7466590664386602e-05,
31
+ "loss": 0.6137,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.48,
36
+ "learning_rate": 1.683323833048325e-05,
37
+ "loss": 0.5306,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.57,
42
+ "learning_rate": 1.6199885996579897e-05,
43
+ "loss": 0.5254,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.67,
48
+ "learning_rate": 1.556653366267655e-05,
49
+ "loss": 0.4436,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.76,
54
+ "learning_rate": 1.4933181328773198e-05,
55
+ "loss": 0.3741,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.86,
60
+ "learning_rate": 1.4299828994869846e-05,
61
+ "loss": 0.3795,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.95,
66
+ "learning_rate": 1.3666476660966497e-05,
67
+ "loss": 0.3805,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.0,
72
+ "eval_loss": 1.1342121362686157,
73
+ "eval_runtime": 354.7905,
74
+ "eval_samples_per_second": 11.88,
75
+ "eval_steps_per_second": 5.942,
76
+ "step": 5263
77
+ },
78
+ {
79
+ "epoch": 1.05,
80
+ "learning_rate": 1.3033124327063148e-05,
81
+ "loss": 0.4431,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 1.14,
86
+ "learning_rate": 1.2399771993159795e-05,
87
+ "loss": 0.2834,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 1.24,
92
+ "learning_rate": 1.1766419659256444e-05,
93
+ "loss": 0.3121,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 1.33,
98
+ "learning_rate": 1.1133067325353095e-05,
99
+ "loss": 0.2991,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 1.43,
104
+ "learning_rate": 1.0499714991449746e-05,
105
+ "loss": 0.3684,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 1.52,
110
+ "learning_rate": 9.866362657546393e-06,
111
+ "loss": 0.2117,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 1.62,
116
+ "learning_rate": 9.233010323643044e-06,
117
+ "loss": 0.2777,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 1.71,
122
+ "learning_rate": 8.599657989739692e-06,
123
+ "loss": 0.249,
124
+ "step": 9000
125
+ }
126
+ ],
127
+ "max_steps": 15789,
128
+ "num_train_epochs": 3,
129
+ "total_flos": 1.2537544393728e+16,
130
+ "trial_name": null,
131
+ "trial_params": null
132
+ }