mikhail-panzo
commited on
Commit
•
81af930
1
Parent(s):
1e99ba1
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:e8d21651e5db2ed67f31319a652131e535151d2fbf4e6b24b3edeb923bb9d99f
|
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:d9f742d32e28e8158fb337c29ed9b09546167bb83f74364f94ebdc185bff0685
|
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 sha256:6e7a2dc2fd34210e38a0dafa68768e7a8ac00e877b03b70d54a43bd027bc5930
|
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 sha256:9cbb951fc4257a68dab12f51ae2258de85fc85dd8c8f4de0474b3e6fac987a51
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.39598318934440613,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-3500",
|
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": 27.369,
|
1100 |
"eval_steps_per_second": 3.497,
|
1101 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1102 |
}
|
1103 |
],
|
1104 |
"logging_steps": 50,
|
@@ -1118,7 +1196,7 @@
|
|
1118 |
"attributes": {}
|
1119 |
}
|
1120 |
},
|
1121 |
-
"total_flos":
|
1122 |
"train_batch_size": 16,
|
1123 |
"trial_name": null,
|
1124 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.39598318934440613,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-3500",
|
4 |
+
"epoch": 297.029702970297,
|
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": 27.369,
|
1100 |
"eval_steps_per_second": 3.497,
|
1101 |
"step": 7000
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 279.2079207920792,
|
1105 |
+
"grad_norm": 0.5922915935516357,
|
1106 |
+
"learning_rate": 1.5850000000000002e-05,
|
1107 |
+
"loss": 0.331,
|
1108 |
+
"step": 7050
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 281.18811881188117,
|
1112 |
+
"grad_norm": 0.49854084849357605,
|
1113 |
+
"learning_rate": 1.5016666666666668e-05,
|
1114 |
+
"loss": 0.3292,
|
1115 |
+
"step": 7100
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 283.16831683168317,
|
1119 |
+
"grad_norm": 0.534227192401886,
|
1120 |
+
"learning_rate": 1.4183333333333335e-05,
|
1121 |
+
"loss": 0.3295,
|
1122 |
+
"step": 7150
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 285.1485148514852,
|
1126 |
+
"grad_norm": 0.4879334568977356,
|
1127 |
+
"learning_rate": 1.3350000000000001e-05,
|
1128 |
+
"loss": 0.3295,
|
1129 |
+
"step": 7200
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 287.1287128712871,
|
1133 |
+
"grad_norm": 0.4761298596858978,
|
1134 |
+
"learning_rate": 1.2516666666666668e-05,
|
1135 |
+
"loss": 0.333,
|
1136 |
+
"step": 7250
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 289.1089108910891,
|
1140 |
+
"grad_norm": 0.5835270881652832,
|
1141 |
+
"learning_rate": 1.1683333333333334e-05,
|
1142 |
+
"loss": 0.3311,
|
1143 |
+
"step": 7300
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 291.08910891089107,
|
1147 |
+
"grad_norm": 0.5297247767448425,
|
1148 |
+
"learning_rate": 1.0866666666666667e-05,
|
1149 |
+
"loss": 0.333,
|
1150 |
+
"step": 7350
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 293.0693069306931,
|
1154 |
+
"grad_norm": 0.44668009877204895,
|
1155 |
+
"learning_rate": 1.0033333333333333e-05,
|
1156 |
+
"loss": 0.3282,
|
1157 |
+
"step": 7400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 295.0495049504951,
|
1161 |
+
"grad_norm": 0.47231703996658325,
|
1162 |
+
"learning_rate": 9.2e-06,
|
1163 |
+
"loss": 0.3309,
|
1164 |
+
"step": 7450
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 297.029702970297,
|
1168 |
+
"grad_norm": 0.5559085011482239,
|
1169 |
+
"learning_rate": 8.366666666666667e-06,
|
1170 |
+
"loss": 0.3345,
|
1171 |
+
"step": 7500
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 297.029702970297,
|
1175 |
+
"eval_loss": 0.40512633323669434,
|
1176 |
+
"eval_runtime": 6.9059,
|
1177 |
+
"eval_samples_per_second": 26.065,
|
1178 |
+
"eval_steps_per_second": 3.33,
|
1179 |
+
"step": 7500
|
1180 |
}
|
1181 |
],
|
1182 |
"logging_steps": 50,
|
|
|
1196 |
"attributes": {}
|
1197 |
}
|
1198 |
},
|
1199 |
+
"total_flos": 8.103931252887646e+16,
|
1200 |
"train_batch_size": 16,
|
1201 |
"trial_name": null,
|
1202 |
"trial_params": null
|