mikhail-panzo
commited on
Commit
•
b3b4924
1
Parent(s):
933d5d7
Training in progress, step 7500, 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:d17f4ae20f9f992a27e6a1fa6cb56310739b4d9e112f20feed6499f8e80bdb75
|
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:b092bb5f421e4613aec93ddde296b498489d2420e7c98850d80363bdeebccfc8
|
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:d880acef54d4eb61cf44bc2962e1f38bf44896cefc09a0303d9df0b77a1ae5c2
|
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:b1e6ef080b2d27380abb32e34a8b58f3a1c18cafb574b45dd697ad5ba8ccc473
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.31849026679992676,
|
3 |
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-7000",
|
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,
|
@@ -1099,6 +1099,84 @@
|
|
1099 |
"eval_samples_per_second": 29.992,
|
1100 |
"eval_steps_per_second": 3.752,
|
1101 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1102 |
}
|
1103 |
],
|
1104 |
"logging_steps": 50,
|
@@ -1118,7 +1196,7 @@
|
|
1118 |
"attributes": {}
|
1119 |
}
|
1120 |
},
|
1121 |
-
"total_flos": 1.
|
1122 |
"train_batch_size": 16,
|
1123 |
"trial_name": null,
|
1124 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.31849026679992676,
|
3 |
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-7000",
|
4 |
+
"epoch": 12.565445026178011,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1099 |
"eval_samples_per_second": 29.992,
|
1100 |
"eval_steps_per_second": 3.752,
|
1101 |
"step": 7000
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 11.81151832460733,
|
1105 |
+
"grad_norm": 1.1094063520431519,
|
1106 |
+
"learning_rate": 4.952e-05,
|
1107 |
+
"loss": 0.346,
|
1108 |
+
"step": 7050
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 11.895287958115183,
|
1112 |
+
"grad_norm": 1.8263230323791504,
|
1113 |
+
"learning_rate": 4.902e-05,
|
1114 |
+
"loss": 0.3496,
|
1115 |
+
"step": 7100
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 11.979057591623036,
|
1119 |
+
"grad_norm": 1.4049593210220337,
|
1120 |
+
"learning_rate": 4.852e-05,
|
1121 |
+
"loss": 0.3433,
|
1122 |
+
"step": 7150
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 12.06282722513089,
|
1126 |
+
"grad_norm": 1.3455963134765625,
|
1127 |
+
"learning_rate": 4.8030000000000006e-05,
|
1128 |
+
"loss": 0.3518,
|
1129 |
+
"step": 7200
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 12.146596858638743,
|
1133 |
+
"grad_norm": 1.174660325050354,
|
1134 |
+
"learning_rate": 4.753e-05,
|
1135 |
+
"loss": 0.348,
|
1136 |
+
"step": 7250
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 12.230366492146597,
|
1140 |
+
"grad_norm": 1.2765902280807495,
|
1141 |
+
"learning_rate": 4.703e-05,
|
1142 |
+
"loss": 0.345,
|
1143 |
+
"step": 7300
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 12.31413612565445,
|
1147 |
+
"grad_norm": 1.419295072555542,
|
1148 |
+
"learning_rate": 4.6530000000000003e-05,
|
1149 |
+
"loss": 0.3436,
|
1150 |
+
"step": 7350
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 12.397905759162304,
|
1154 |
+
"grad_norm": 1.3437247276306152,
|
1155 |
+
"learning_rate": 4.603e-05,
|
1156 |
+
"loss": 0.3469,
|
1157 |
+
"step": 7400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 12.481675392670157,
|
1161 |
+
"grad_norm": 1.6074751615524292,
|
1162 |
+
"learning_rate": 4.553e-05,
|
1163 |
+
"loss": 0.3461,
|
1164 |
+
"step": 7450
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 12.565445026178011,
|
1168 |
+
"grad_norm": 1.432062029838562,
|
1169 |
+
"learning_rate": 4.503e-05,
|
1170 |
+
"loss": 0.3441,
|
1171 |
+
"step": 7500
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 12.565445026178011,
|
1175 |
+
"eval_loss": 0.3222896158695221,
|
1176 |
+
"eval_runtime": 282.6486,
|
1177 |
+
"eval_samples_per_second": 30.034,
|
1178 |
+
"eval_steps_per_second": 3.757,
|
1179 |
+
"step": 7500
|
1180 |
}
|
1181 |
],
|
1182 |
"logging_steps": 50,
|
|
|
1196 |
"attributes": {}
|
1197 |
}
|
1198 |
},
|
1199 |
+
"total_flos": 1.3437364892618304e+17,
|
1200 |
"train_batch_size": 16,
|
1201 |
"trial_name": null,
|
1202 |
"trial_params": null
|