root commited on
Commit
b48f5ec
1 Parent(s): fd0d790
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6667ff94425aaa5ff75b2c159cce162423e7457f7587b00b8c1458d7319baa1
3
+ size 33629893
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27212d4a658166f71418ec7f9fa368839a86a429c6c352fba4ddd290ce7dbf80
3
+ size 7023334881
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0494f897755c11a1d6ee778ed960dce2c788754092bb0e157e9abaa41b7bb52
3
+ size 14575
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27deb6c1317f6d7dfdc532a327d645b3a9c3eba897c490955f7d425ab9b976cc
3
+ size 557
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c999bca8f6d41d0b9498c44dc90b53e9466f2a1b56b41ac4e393b0bdc4fc967f
3
+ size 627
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.088978766430738,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.32,
12
+ "learning_rate": 1.9803278688524592e-05,
13
+ "loss": 1.9325,
14
+ "step": 20
15
+ },
16
+ {
17
+ "epoch": 0.65,
18
+ "learning_rate": 1.9595628415300548e-05,
19
+ "loss": 1.7877,
20
+ "step": 40
21
+ },
22
+ {
23
+ "epoch": 0.97,
24
+ "learning_rate": 1.937704918032787e-05,
25
+ "loss": 1.6385,
26
+ "step": 60
27
+ },
28
+ {
29
+ "epoch": 1.29,
30
+ "learning_rate": 1.9158469945355195e-05,
31
+ "loss": 1.5616,
32
+ "step": 80
33
+ },
34
+ {
35
+ "epoch": 1.62,
36
+ "learning_rate": 1.8939890710382515e-05,
37
+ "loss": 1.4152,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 1.94,
42
+ "learning_rate": 1.873224043715847e-05,
43
+ "loss": 1.3212,
44
+ "step": 120
45
+ },
46
+ {
47
+ "epoch": 2.26,
48
+ "learning_rate": 1.8513661202185794e-05,
49
+ "loss": 1.2661,
50
+ "step": 140
51
+ },
52
+ {
53
+ "epoch": 2.59,
54
+ "learning_rate": 1.8295081967213114e-05,
55
+ "loss": 1.1635,
56
+ "step": 160
57
+ },
58
+ {
59
+ "epoch": 2.91,
60
+ "learning_rate": 1.807650273224044e-05,
61
+ "loss": 1.083,
62
+ "step": 180
63
+ },
64
+ {
65
+ "epoch": 3.24,
66
+ "learning_rate": 1.785792349726776e-05,
67
+ "loss": 1.0087,
68
+ "step": 200
69
+ },
70
+ {
71
+ "epoch": 3.56,
72
+ "learning_rate": 1.7639344262295085e-05,
73
+ "loss": 0.9656,
74
+ "step": 220
75
+ },
76
+ {
77
+ "epoch": 3.88,
78
+ "learning_rate": 1.7420765027322405e-05,
79
+ "loss": 0.9752,
80
+ "step": 240
81
+ },
82
+ {
83
+ "epoch": 4.21,
84
+ "learning_rate": 1.720218579234973e-05,
85
+ "loss": 0.9144,
86
+ "step": 260
87
+ },
88
+ {
89
+ "epoch": 4.53,
90
+ "learning_rate": 1.6983606557377052e-05,
91
+ "loss": 0.8767,
92
+ "step": 280
93
+ },
94
+ {
95
+ "epoch": 4.85,
96
+ "learning_rate": 1.6765027322404372e-05,
97
+ "loss": 0.8613,
98
+ "step": 300
99
+ },
100
+ {
101
+ "epoch": 5.18,
102
+ "learning_rate": 1.6546448087431696e-05,
103
+ "loss": 0.8689,
104
+ "step": 320
105
+ },
106
+ {
107
+ "epoch": 5.5,
108
+ "learning_rate": 1.6327868852459016e-05,
109
+ "loss": 0.778,
110
+ "step": 340
111
+ },
112
+ {
113
+ "epoch": 5.82,
114
+ "learning_rate": 1.6109289617486343e-05,
115
+ "loss": 0.7594,
116
+ "step": 360
117
+ },
118
+ {
119
+ "epoch": 6.15,
120
+ "learning_rate": 1.5890710382513663e-05,
121
+ "loss": 0.756,
122
+ "step": 380
123
+ },
124
+ {
125
+ "epoch": 6.47,
126
+ "learning_rate": 1.5672131147540986e-05,
127
+ "loss": 0.7412,
128
+ "step": 400
129
+ },
130
+ {
131
+ "epoch": 6.79,
132
+ "learning_rate": 1.5453551912568306e-05,
133
+ "loss": 0.6841,
134
+ "step": 420
135
+ },
136
+ {
137
+ "epoch": 7.12,
138
+ "learning_rate": 1.523497267759563e-05,
139
+ "loss": 0.6709,
140
+ "step": 440
141
+ },
142
+ {
143
+ "epoch": 7.44,
144
+ "learning_rate": 1.5016393442622952e-05,
145
+ "loss": 0.6456,
146
+ "step": 460
147
+ },
148
+ {
149
+ "epoch": 7.77,
150
+ "learning_rate": 1.4797814207650274e-05,
151
+ "loss": 0.6366,
152
+ "step": 480
153
+ },
154
+ {
155
+ "epoch": 8.09,
156
+ "learning_rate": 1.4579234972677595e-05,
157
+ "loss": 0.6762,
158
+ "step": 500
159
+ }
160
+ ],
161
+ "max_steps": 1830,
162
+ "num_train_epochs": 30,
163
+ "total_flos": 1.2995638935552e+18,
164
+ "trial_name": null,
165
+ "trial_params": null
166
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a8a3ab7979c24c11ed2e8e59bda7617c174ede7f48976d8989449ea69f3fbc
3
+ size 3899
runs/May04_06-11-56_n7dif8lxn7/1683180716.2456856/events.out.tfevents.1683180716.n7dif8lxn7.6367.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4ab679d8fb88d68891eae9c280584e0e19b53c98297a998345ba1b55a38b8bc
3
+ size 5839
runs/May04_06-11-56_n7dif8lxn7/events.out.tfevents.1683180716.n7dif8lxn7.6367.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0af0eb55b1ed8a7fbae714f2263fdcf8966483d39c2c9fbc61bdf1d7ac497f
3
+ size 8613