Commit
•
25225e5
1
Parent(s):
f746706
Training in progress, step 6500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7a9ff8c6f099453e24c907ca48e18d629eeebd26b25e5d67dd78c92f08d9ec7
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7dbfca172321951aa3408c63e50180be9688454b3122fc35e2e279441fcd5a2
|
3 |
size 1155772233
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc4bf9efeacd197a3755be03d6b9b32a091466296d5d750906cf5632d21aec65
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9050220365c3d4317bfb9eee77e3abcc137e10ebf0d1b1a7e4370a6b88a28327
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-
|
4 |
-
"epoch": 10.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -943,6 +943,84 @@
|
|
943 |
"eval_samples_per_second": 31.055,
|
944 |
"eval_steps_per_second": 3.885,
|
945 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
946 |
}
|
947 |
],
|
948 |
"logging_steps": 50,
|
@@ -962,7 +1040,7 @@
|
|
962 |
"attributes": {}
|
963 |
}
|
964 |
},
|
965 |
-
"total_flos": 1.
|
966 |
"train_batch_size": 16,
|
967 |
"trial_name": null,
|
968 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.31707289814949036,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-6500",
|
4 |
+
"epoch": 10.890052356020943,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 6500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
943 |
"eval_samples_per_second": 31.055,
|
944 |
"eval_steps_per_second": 3.885,
|
945 |
"step": 6000
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 10.136125654450261,
|
949 |
+
"grad_norm": 1.572178840637207,
|
950 |
+
"learning_rate": 3.253333333333333e-05,
|
951 |
+
"loss": 0.3492,
|
952 |
+
"step": 6050
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 10.219895287958115,
|
956 |
+
"grad_norm": 1.063959002494812,
|
957 |
+
"learning_rate": 3.1700000000000005e-05,
|
958 |
+
"loss": 0.3525,
|
959 |
+
"step": 6100
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 10.303664921465968,
|
963 |
+
"grad_norm": 1.1579703092575073,
|
964 |
+
"learning_rate": 3.086666666666667e-05,
|
965 |
+
"loss": 0.3486,
|
966 |
+
"step": 6150
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 10.387434554973822,
|
970 |
+
"grad_norm": 1.4260714054107666,
|
971 |
+
"learning_rate": 3.0033333333333336e-05,
|
972 |
+
"loss": 0.3483,
|
973 |
+
"step": 6200
|
974 |
+
},
|
975 |
+
{
|
976 |
+
"epoch": 10.471204188481675,
|
977 |
+
"grad_norm": 1.453321099281311,
|
978 |
+
"learning_rate": 2.9199999999999998e-05,
|
979 |
+
"loss": 0.3481,
|
980 |
+
"step": 6250
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 10.55497382198953,
|
984 |
+
"grad_norm": 1.8545498847961426,
|
985 |
+
"learning_rate": 2.836666666666667e-05,
|
986 |
+
"loss": 0.3482,
|
987 |
+
"step": 6300
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 10.638743455497382,
|
991 |
+
"grad_norm": 1.073957920074463,
|
992 |
+
"learning_rate": 2.7533333333333333e-05,
|
993 |
+
"loss": 0.348,
|
994 |
+
"step": 6350
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 10.722513089005236,
|
998 |
+
"grad_norm": 1.0049316883087158,
|
999 |
+
"learning_rate": 2.6700000000000002e-05,
|
1000 |
+
"loss": 0.3487,
|
1001 |
+
"step": 6400
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 10.806282722513089,
|
1005 |
+
"grad_norm": 1.4970500469207764,
|
1006 |
+
"learning_rate": 2.5866666666666667e-05,
|
1007 |
+
"loss": 0.3468,
|
1008 |
+
"step": 6450
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 10.890052356020943,
|
1012 |
+
"grad_norm": 1.6566526889801025,
|
1013 |
+
"learning_rate": 2.5033333333333336e-05,
|
1014 |
+
"loss": 0.3469,
|
1015 |
+
"step": 6500
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 10.890052356020943,
|
1019 |
+
"eval_loss": 0.31707289814949036,
|
1020 |
+
"eval_runtime": 275.2143,
|
1021 |
+
"eval_samples_per_second": 30.845,
|
1022 |
+
"eval_steps_per_second": 3.859,
|
1023 |
+
"step": 6500
|
1024 |
}
|
1025 |
],
|
1026 |
"logging_steps": 50,
|
|
|
1040 |
"attributes": {}
|
1041 |
}
|
1042 |
},
|
1043 |
+
"total_flos": 1.1645139306201984e+17,
|
1044 |
"train_batch_size": 16,
|
1045 |
"trial_name": null,
|
1046 |
"trial_params": null
|