loss 0.8
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +87 -45
- training_args.bin +1 -1
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1376950965
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f47f9dfd4db9c9ec151a63abad536764855bc77ae7c5b51d92a7ac5356d68ac7
|
3 |
size 1376950965
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 688496379
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e18c81df99acab8af427dd3790e53aeb09b6ade90fb6de29bdb78209b43d114b
|
3 |
size 688496379
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da8a2f50723c6317cb8a013b2809dff53084c39ff9282e5af6824bf995015112
|
3 |
size 14503
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23b550aa2fbfa2b125c031925d9d10c08ba2222b1d741f4334fc52524cc99d50
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,94 +1,136 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
{
|
11 |
"epoch": 0.03,
|
12 |
"learning_rate": 0.0006977191267513849,
|
13 |
-
"loss": 0.
|
14 |
"step": 300
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
{
|
17 |
"epoch": 0.07,
|
18 |
"learning_rate": 0.0006954382535027696,
|
19 |
-
"loss": 0.
|
20 |
"step": 600
|
21 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
{
|
23 |
"epoch": 0.1,
|
24 |
"learning_rate": 0.0006931573802541545,
|
25 |
-
"loss": 0.
|
26 |
"step": 900
|
27 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
{
|
29 |
"epoch": 0.13,
|
30 |
"learning_rate": 0.0006908765070055393,
|
31 |
-
"loss": 0.
|
32 |
"step": 1200
|
33 |
},
|
34 |
{
|
35 |
-
"epoch": 0.
|
36 |
-
"learning_rate": 0.
|
37 |
-
"loss": 0.
|
38 |
-
"step":
|
39 |
},
|
40 |
{
|
41 |
-
"epoch": 0.
|
42 |
-
"learning_rate": 0.
|
43 |
-
"loss": 0.
|
44 |
-
"step":
|
45 |
},
|
46 |
{
|
47 |
-
"epoch": 0.
|
48 |
-
"learning_rate": 0.
|
49 |
-
"loss": 0.
|
50 |
-
"step":
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.26,
|
54 |
-
"learning_rate": 0.0006817530140110785,
|
55 |
-
"loss": 0.9114,
|
56 |
-
"step": 2400
|
57 |
},
|
58 |
{
|
59 |
-
"epoch": 0.
|
60 |
-
"learning_rate": 0.
|
61 |
-
"loss": 0.
|
62 |
-
"step":
|
63 |
},
|
64 |
{
|
65 |
-
"epoch": 0.
|
66 |
-
"learning_rate": 0.
|
67 |
-
"loss": 0.
|
68 |
-
"step":
|
69 |
},
|
70 |
{
|
71 |
-
"epoch": 0.
|
72 |
-
"learning_rate": 0.
|
73 |
-
"loss": 0.
|
74 |
-
"step":
|
75 |
},
|
76 |
{
|
77 |
-
"epoch": 0.
|
78 |
-
"learning_rate": 0.
|
79 |
-
"loss": 0.
|
80 |
-
"step":
|
81 |
},
|
82 |
{
|
83 |
-
"epoch": 0.
|
84 |
-
"learning_rate": 0.
|
85 |
-
"loss": 0.
|
86 |
-
"step":
|
87 |
}
|
88 |
],
|
89 |
"max_steps": 92070,
|
90 |
"num_train_epochs": 10,
|
91 |
-
"total_flos":
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|
94 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.21722012544462244,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 0.0006992397089171283,
|
13 |
+
"loss": 0.6909,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"learning_rate": 0.0006984794178342565,
|
19 |
+
"loss": 0.7334,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
{
|
23 |
"epoch": 0.03,
|
24 |
"learning_rate": 0.0006977191267513849,
|
25 |
+
"loss": 0.7397,
|
26 |
"step": 300
|
27 |
},
|
28 |
+
{
|
29 |
+
"epoch": 0.04,
|
30 |
+
"learning_rate": 0.0006969588356685131,
|
31 |
+
"loss": 0.7262,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.05,
|
36 |
+
"learning_rate": 0.0006961985445856413,
|
37 |
+
"loss": 0.7232,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
{
|
41 |
"epoch": 0.07,
|
42 |
"learning_rate": 0.0006954382535027696,
|
43 |
+
"loss": 0.7182,
|
44 |
"step": 600
|
45 |
},
|
46 |
+
{
|
47 |
+
"epoch": 0.08,
|
48 |
+
"learning_rate": 0.0006946779624198979,
|
49 |
+
"loss": 0.7438,
|
50 |
+
"step": 700
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.09,
|
54 |
+
"learning_rate": 0.0006939176713370262,
|
55 |
+
"loss": 0.7207,
|
56 |
+
"step": 800
|
57 |
+
},
|
58 |
{
|
59 |
"epoch": 0.1,
|
60 |
"learning_rate": 0.0006931573802541545,
|
61 |
+
"loss": 0.7147,
|
62 |
"step": 900
|
63 |
},
|
64 |
+
{
|
65 |
+
"epoch": 0.11,
|
66 |
+
"learning_rate": 0.0006923970891712827,
|
67 |
+
"loss": 0.7547,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.12,
|
72 |
+
"learning_rate": 0.0006916367980884109,
|
73 |
+
"loss": 0.7609,
|
74 |
+
"step": 1100
|
75 |
+
},
|
76 |
{
|
77 |
"epoch": 0.13,
|
78 |
"learning_rate": 0.0006908765070055393,
|
79 |
+
"loss": 0.7163,
|
80 |
"step": 1200
|
81 |
},
|
82 |
{
|
83 |
+
"epoch": 0.14,
|
84 |
+
"learning_rate": 0.0006901162159226675,
|
85 |
+
"loss": 0.7518,
|
86 |
+
"step": 1300
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 0.15,
|
90 |
+
"learning_rate": 0.0006893559248397958,
|
91 |
+
"loss": 0.7698,
|
92 |
+
"step": 1400
|
93 |
},
|
94 |
{
|
95 |
+
"epoch": 0.16,
|
96 |
+
"learning_rate": 0.0006885956337569241,
|
97 |
+
"loss": 0.7327,
|
98 |
+
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
99 |
},
|
100 |
{
|
101 |
+
"epoch": 0.17,
|
102 |
+
"learning_rate": 0.0006878353426740524,
|
103 |
+
"loss": 0.7871,
|
104 |
+
"step": 1600
|
105 |
},
|
106 |
{
|
107 |
+
"epoch": 0.18,
|
108 |
+
"learning_rate": 0.0006870750515911806,
|
109 |
+
"loss": 0.7908,
|
110 |
+
"step": 1700
|
111 |
},
|
112 |
{
|
113 |
+
"epoch": 0.2,
|
114 |
+
"learning_rate": 0.0006863147605083089,
|
115 |
+
"loss": 0.7646,
|
116 |
+
"step": 1800
|
117 |
},
|
118 |
{
|
119 |
+
"epoch": 0.21,
|
120 |
+
"learning_rate": 0.0006855544694254371,
|
121 |
+
"loss": 0.7677,
|
122 |
+
"step": 1900
|
123 |
},
|
124 |
{
|
125 |
+
"epoch": 0.22,
|
126 |
+
"learning_rate": 0.0006847941783425654,
|
127 |
+
"loss": 0.7533,
|
128 |
+
"step": 2000
|
129 |
}
|
130 |
],
|
131 |
"max_steps": 92070,
|
132 |
"num_train_epochs": 10,
|
133 |
+
"total_flos": 4097763812966400.0,
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2607
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bf29105b2f1e653c8eadf07726bc244d198013decfeabceefd5896a51895501
|
3 |
size 2607
|