Commit
•
c928325
1
Parent(s):
948c462
Training in progress, step 7000, 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:cce8730ec7977cf6faded9c8a64710dd40c64e82312111fdae82ba0e37b6fe02
|
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 sha256:7d0bacbf128b4eb958fabc358356f531f65f6bd424a2a9be5add80fa30ab7cff
|
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:a59b056016e351429f719aaf02cc6fa4544a2d92d2a3d69beeeb56674b12a1f2
|
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:a48d9034d2ce2771f0a840f8364e39645d6f213d3858f7f5342b741dc49975d2
|
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":
|
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,
|
@@ -1021,6 +1021,84 @@
|
|
1021 |
"eval_samples_per_second": 30.845,
|
1022 |
"eval_steps_per_second": 3.859,
|
1023 |
"step": 6500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1024 |
}
|
1025 |
],
|
1026 |
"logging_steps": 50,
|
@@ -1040,7 +1118,7 @@
|
|
1040 |
"attributes": {}
|
1041 |
}
|
1042 |
},
|
1043 |
-
"total_flos": 1.
|
1044 |
"train_batch_size": 16,
|
1045 |
"trial_name": null,
|
1046 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.31611359119415283,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-7000",
|
4 |
+
"epoch": 11.727748691099476,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1021 |
"eval_samples_per_second": 30.845,
|
1022 |
"eval_steps_per_second": 3.859,
|
1023 |
"step": 6500
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 10.973821989528796,
|
1027 |
+
"grad_norm": 1.1960996389389038,
|
1028 |
+
"learning_rate": 2.4200000000000002e-05,
|
1029 |
+
"loss": 0.3478,
|
1030 |
+
"step": 6550
|
1031 |
+
},
|
1032 |
+
{
|
1033 |
+
"epoch": 11.057591623036648,
|
1034 |
+
"grad_norm": 0.97001713514328,
|
1035 |
+
"learning_rate": 2.3366666666666668e-05,
|
1036 |
+
"loss": 0.3475,
|
1037 |
+
"step": 6600
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 11.141361256544503,
|
1041 |
+
"grad_norm": 1.1384519338607788,
|
1042 |
+
"learning_rate": 2.2533333333333333e-05,
|
1043 |
+
"loss": 0.3484,
|
1044 |
+
"step": 6650
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 11.225130890052355,
|
1048 |
+
"grad_norm": 0.9649496078491211,
|
1049 |
+
"learning_rate": 2.1700000000000002e-05,
|
1050 |
+
"loss": 0.3454,
|
1051 |
+
"step": 6700
|
1052 |
+
},
|
1053 |
+
{
|
1054 |
+
"epoch": 11.30890052356021,
|
1055 |
+
"grad_norm": 1.0407809019088745,
|
1056 |
+
"learning_rate": 2.0866666666666668e-05,
|
1057 |
+
"loss": 0.3446,
|
1058 |
+
"step": 6750
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 11.392670157068062,
|
1062 |
+
"grad_norm": 1.087108850479126,
|
1063 |
+
"learning_rate": 2.0033333333333334e-05,
|
1064 |
+
"loss": 0.3475,
|
1065 |
+
"step": 6800
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 11.476439790575917,
|
1069 |
+
"grad_norm": 0.8870049715042114,
|
1070 |
+
"learning_rate": 1.9200000000000003e-05,
|
1071 |
+
"loss": 0.3454,
|
1072 |
+
"step": 6850
|
1073 |
+
},
|
1074 |
+
{
|
1075 |
+
"epoch": 11.56020942408377,
|
1076 |
+
"grad_norm": 1.0377373695373535,
|
1077 |
+
"learning_rate": 1.8366666666666668e-05,
|
1078 |
+
"loss": 0.3447,
|
1079 |
+
"step": 6900
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 11.643979057591624,
|
1083 |
+
"grad_norm": 1.138604760169983,
|
1084 |
+
"learning_rate": 1.7533333333333334e-05,
|
1085 |
+
"loss": 0.345,
|
1086 |
+
"step": 6950
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 11.727748691099476,
|
1090 |
+
"grad_norm": 1.6464053392410278,
|
1091 |
+
"learning_rate": 1.6700000000000003e-05,
|
1092 |
+
"loss": 0.3465,
|
1093 |
+
"step": 7000
|
1094 |
+
},
|
1095 |
+
{
|
1096 |
+
"epoch": 11.727748691099476,
|
1097 |
+
"eval_loss": 0.31611359119415283,
|
1098 |
+
"eval_runtime": 271.5426,
|
1099 |
+
"eval_samples_per_second": 31.262,
|
1100 |
+
"eval_steps_per_second": 3.911,
|
1101 |
+
"step": 7000
|
1102 |
}
|
1103 |
],
|
1104 |
"logging_steps": 50,
|
|
|
1118 |
"attributes": {}
|
1119 |
}
|
1120 |
},
|
1121 |
+
"total_flos": 1.2541009593096864e+17,
|
1122 |
"train_batch_size": 16,
|
1123 |
"trial_name": null,
|
1124 |
"trial_params": null
|