Training in progress, step 10000, checkpoint
Browse files- last-checkpoint/global_step10000/mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step10000/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step10000/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step10000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step10000/zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step10000/zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step10000/zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/latest +1 -1
- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +2 -2
- last-checkpoint/rng_state_4.pth +2 -2
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +73 -3
last-checkpoint/global_step10000/mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:986c5d6189f91975e918f7f6617810450fb7b51890d876a741c390d4841f7b69
|
3 |
+
size 197282509
|
last-checkpoint/global_step10000/zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbb6697e7d09b2b9438e99b4121c3d6aacb691a415048f42e8ceedd7e4b39aa5
|
3 |
+
size 180416968
|
last-checkpoint/global_step10000/zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed54d6bb08e4df0fe2cb8d14b5ee65221041a04809718255aad9ffa15386977d
|
3 |
+
size 180416776
|
last-checkpoint/global_step10000/zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:681803b8fe75cdc69741908fb444d099d93b1a4452c3aa526d209dbf9c1b4e9e
|
3 |
+
size 180416776
|
last-checkpoint/global_step10000/zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32c4c01a8df2ddf6f4bf201fe6150e9914144ea8d563e055a7617f855c7d3cf7
|
3 |
+
size 180416904
|
last-checkpoint/global_step10000/zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6b3ab5eb9405f2cc1b4cdc0893c7fd00063d1174a35330b50c91d82c09e5b1f
|
3 |
+
size 180416712
|
last-checkpoint/global_step10000/zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee11d6dcd3ad95295de240130db341c0d7a9435fe8ed7cd54769171b466da104
|
3 |
+
size 180417096
|
last-checkpoint/latest
CHANGED
@@ -1 +1 @@
|
|
1 |
-
|
|
|
1 |
+
global_step10000
|
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 188836816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e2cf95851453659172edee862761d076db580a680ad8053dff69e4287a74cd6
|
3 |
size 188836816
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b89fe0482199ff808b868b8a0a46d2f0637b6dc06af9dc1ffbdeda6857c3071a
|
3 |
size 15536
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84bf853cfccab8ac65f8578c2fb423680b3549ae90b19876fa0965424652b821
|
3 |
size 15536
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3a3b603dad6931c9b06331e262a9b1593f8b87b28b513dd9f71508cb34c588a
|
3 |
size 15536
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d46f1d9fed83d2d3a6a159e06e1b60d78d2703f069254cc21b859ac0703b80a
|
3 |
+
size 15472
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:902357280c996bfa97fdb46106f3a627456487652f274eb8f738ed7ee589e62c
|
3 |
+
size 15472
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cc5274efbac0d8700f57b902965cc1eb74b479df838f79d33f9b7fd9c1f9e74
|
3 |
size 15536
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60915f9b39e366db12f97cc58cc8fc51304f5d2a2df70683329578a0e59cb1bf
|
3 |
size 1256
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 1500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1382,6 +1382,76 @@
|
|
1382 |
"learning_rate": 0.0001,
|
1383 |
"loss": 0.0194,
|
1384 |
"step": 9500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1385 |
}
|
1386 |
],
|
1387 |
"logging_steps": 50,
|
@@ -1401,7 +1471,7 @@
|
|
1401 |
"attributes": {}
|
1402 |
}
|
1403 |
},
|
1404 |
-
"total_flos": 2.
|
1405 |
"train_batch_size": 64,
|
1406 |
"trial_name": null,
|
1407 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 270.27027027027026,
|
5 |
"eval_steps": 1500,
|
6 |
+
"global_step": 10000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1382 |
"learning_rate": 0.0001,
|
1383 |
"loss": 0.0194,
|
1384 |
"step": 9500
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 258.1081081081081,
|
1388 |
+
"grad_norm": 0.30529114603996277,
|
1389 |
+
"learning_rate": 0.0001,
|
1390 |
+
"loss": 0.0186,
|
1391 |
+
"step": 9550
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 259.4594594594595,
|
1395 |
+
"grad_norm": 0.257412314414978,
|
1396 |
+
"learning_rate": 0.0001,
|
1397 |
+
"loss": 0.018,
|
1398 |
+
"step": 9600
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 260.81081081081084,
|
1402 |
+
"grad_norm": 0.34228768944740295,
|
1403 |
+
"learning_rate": 0.0001,
|
1404 |
+
"loss": 0.019,
|
1405 |
+
"step": 9650
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 262.1621621621622,
|
1409 |
+
"grad_norm": 0.43392807245254517,
|
1410 |
+
"learning_rate": 0.0001,
|
1411 |
+
"loss": 0.0188,
|
1412 |
+
"step": 9700
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 263.5135135135135,
|
1416 |
+
"grad_norm": 0.2830718457698822,
|
1417 |
+
"learning_rate": 0.0001,
|
1418 |
+
"loss": 0.0191,
|
1419 |
+
"step": 9750
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 264.86486486486484,
|
1423 |
+
"grad_norm": 0.33202308416366577,
|
1424 |
+
"learning_rate": 0.0001,
|
1425 |
+
"loss": 0.0179,
|
1426 |
+
"step": 9800
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 266.2162162162162,
|
1430 |
+
"grad_norm": 0.4601031243801117,
|
1431 |
+
"learning_rate": 0.0001,
|
1432 |
+
"loss": 0.0176,
|
1433 |
+
"step": 9850
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 267.56756756756755,
|
1437 |
+
"grad_norm": 0.33976060152053833,
|
1438 |
+
"learning_rate": 0.0001,
|
1439 |
+
"loss": 0.0183,
|
1440 |
+
"step": 9900
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 268.9189189189189,
|
1444 |
+
"grad_norm": 0.23951521515846252,
|
1445 |
+
"learning_rate": 0.0001,
|
1446 |
+
"loss": 0.0171,
|
1447 |
+
"step": 9950
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 270.27027027027026,
|
1451 |
+
"grad_norm": 0.7073889970779419,
|
1452 |
+
"learning_rate": 0.0001,
|
1453 |
+
"loss": 0.0165,
|
1454 |
+
"step": 10000
|
1455 |
}
|
1456 |
],
|
1457 |
"logging_steps": 50,
|
|
|
1471 |
"attributes": {}
|
1472 |
}
|
1473 |
},
|
1474 |
+
"total_flos": 2.80706148015297e+20,
|
1475 |
"train_batch_size": 64,
|
1476 |
"trial_name": null,
|
1477 |
"trial_params": null
|