GnanaPraveen commited on
Commit
b76fd98
·
verified ·
1 Parent(s): d91d272

Upload verified RESUME_STATE_LOCAL.json

Browse files
Files changed (1) hide show
  1. RESUME_STATE_LOCAL.json +80 -0
RESUME_STATE_LOCAL.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "original_path": "/data3/praveen/experiments/vpp2-recovery55-no-kv-to1000-20261103/recovery/checkpoints/update_001000",
3
+ "reason": "Full optimizer/resume shards exceed the personal free-tier private-storage allowance and are deferred pending destination selection.",
4
+ "receipt": {
5
+ "checkpoint_identity": "2899ec0a0f6af889a1babd95c7475e7bc6449b39b12b354384964f5abd30d388",
6
+ "files": {
7
+ "bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt": {
8
+ "sha256": "0d33035235009137414b82d1d8e08f8042e3b6b2a5751f8078ee7eb66d7c4dee",
9
+ "size": 17208428484
10
+ },
11
+ "bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt": {
12
+ "sha256": "85ea00ab82114fe05b62f0441b8615f5e2c569d4cdee1cd0d7eaee96243fed63",
13
+ "size": 17213174428
14
+ },
15
+ "bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt": {
16
+ "sha256": "37c505863a1129efe703fd34d992b45adc440e9dd93bd1306da9d39aa856a0a8",
17
+ "size": 17211998172
18
+ },
19
+ "bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt": {
20
+ "sha256": "923d3b5fde2d350eb134cc3bfc93a6a98d589b0ef062d8ee945c184cf4422539",
21
+ "size": 17214269733
22
+ },
23
+ "bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt": {
24
+ "sha256": "c362c831a50935204078a434f05862560d4657d61a2d822f4bade80ab8ec4751",
25
+ "size": 17211683350
26
+ },
27
+ "bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt": {
28
+ "sha256": "9ff16b0c5a15154c6e486d206379ac70f58fb8a156be12ed7ba777d537ccba76",
29
+ "size": 17205282759
30
+ },
31
+ "bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt": {
32
+ "sha256": "d3d625ded0abb49ae560a5a9e7356f2f345246f6d2deb1fbf492a8c3dde3a68d",
33
+ "size": 17193645344
34
+ },
35
+ "bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt": {
36
+ "sha256": "b64e40e2b433e0a95f28ccebd0f3fa899f2bedfb77ef62a9b0371e3f093a21a0",
37
+ "size": 17196229893
38
+ },
39
+ "zero_pp_rank_0_mp_rank_00_model_states.pt": {
40
+ "sha256": "4eec7353b2f34dbfff54df2013f5261bb20643e1509760766f02686d37d4a94e",
41
+ "size": 78779
42
+ },
43
+ "zero_pp_rank_1_mp_rank_00_model_states.pt": {
44
+ "sha256": "ab1b0fd39ea72506f2d8f74d570968e646c01ca82f3cd04705d888b137f74090",
45
+ "size": 78783
46
+ },
47
+ "zero_pp_rank_2_mp_rank_00_model_states.pt": {
48
+ "sha256": "30082af65f03a955dc837eb72eebf1dc2dc1aec23af1f5d20eef1a9f6edae2fe",
49
+ "size": 78780
50
+ },
51
+ "zero_pp_rank_3_mp_rank_00_model_states.pt": {
52
+ "sha256": "126b9d5641ba0e0c59967ef41285771ad5c76e70a8f8896c745fb9a4f1b54a81",
53
+ "size": 78781
54
+ },
55
+ "zero_pp_rank_4_mp_rank_00_model_states.pt": {
56
+ "sha256": "93278bc910a03046b2463d964d4187d2d6ae7ddd33b3f1f039aaf425b0dc8924",
57
+ "size": 78782
58
+ },
59
+ "zero_pp_rank_5_mp_rank_00_model_states.pt": {
60
+ "sha256": "a63df2fdeb27465b234d0f9f32283a86043d38a6e85a96fc89d16046fe5f4c22",
61
+ "size": 78770
62
+ },
63
+ "zero_pp_rank_6_mp_rank_00_model_states.pt": {
64
+ "sha256": "c7cad4d47a16c0a1bc33e39255001ac3c0b61e7fcdb36ccb337483e4d83a46a8",
65
+ "size": 78779
66
+ },
67
+ "zero_pp_rank_7_mp_rank_00_model_states.pt": {
68
+ "sha256": "43029cb15da85321fff5e2751376e7178dd239c852d92a6dbc3d73d1ab8db0f2",
69
+ "size": 78779
70
+ }
71
+ },
72
+ "identity": "790bffc9464fa7a026aa43b217aec2033d186895cad643166daa0bcc01914d5c",
73
+ "mask_identity": null,
74
+ "recovery_export_sha256": "2917adfeadbc2c6d4da60b7739dbee861d7f318f8fc66877f1ca6bd691938172",
75
+ "stage": "recovery",
76
+ "update": 1000
77
+ },
78
+ "total_shard_bytes": 137655342396,
79
+ "uploaded": false
80
+ }