Commit
•
62e7aa5
1
Parent(s):
fa93c98
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 sha256:403cfbffc7ee4007065e4824a75bc209469efb1d3eaf4b78bdcdc4b8e425ae79
|
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 sha256:7f82a7c0b927ee4293785e8b97633d22c4746dbad1b0c92376ee3f5578e79116
|
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 sha256:795fe76cfd6ac22612e53f90e3708fe6447c8d1c969f78a57978bb17493086b1
|
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 sha256:2ef84ad524da6dbaaadb8576fa258a66ac5d4b080583a172fefc45887ff84f46
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.41427454352378845,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b128_le3_s8000/checkpoint-500",
|
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": 26.722,
|
1100 |
"eval_steps_per_second": 3.415,
|
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": 32,
|
1123 |
"trial_name": null,
|
1124 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.41427454352378845,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b128_le3_s8000/checkpoint-500",
|
4 |
+
"epoch": 588.2352941176471,
|
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": 26.722,
|
1100 |
"eval_steps_per_second": 3.415,
|
1101 |
"step": 7000
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 552.9411764705883,
|
1105 |
+
"grad_norm": 0.06083720177412033,
|
1106 |
+
"learning_rate": 0.00015866666666666668,
|
1107 |
+
"loss": 1.42,
|
1108 |
+
"step": 7050
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 556.8627450980392,
|
1112 |
+
"grad_norm": 0.07482324540615082,
|
1113 |
+
"learning_rate": 0.00015033333333333335,
|
1114 |
+
"loss": 1.4184,
|
1115 |
+
"step": 7100
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 560.7843137254902,
|
1119 |
+
"grad_norm": 0.05342550203204155,
|
1120 |
+
"learning_rate": 0.00014199999999999998,
|
1121 |
+
"loss": 1.4186,
|
1122 |
+
"step": 7150
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 564.7058823529412,
|
1126 |
+
"grad_norm": 0.09053777158260345,
|
1127 |
+
"learning_rate": 0.00013366666666666667,
|
1128 |
+
"loss": 1.4191,
|
1129 |
+
"step": 7200
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 568.6274509803922,
|
1133 |
+
"grad_norm": 0.08072460442781448,
|
1134 |
+
"learning_rate": 0.00012533333333333334,
|
1135 |
+
"loss": 1.42,
|
1136 |
+
"step": 7250
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 572.5490196078431,
|
1140 |
+
"grad_norm": 0.09836099296808243,
|
1141 |
+
"learning_rate": 0.00011700000000000001,
|
1142 |
+
"loss": 1.4193,
|
1143 |
+
"step": 7300
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 576.4705882352941,
|
1147 |
+
"grad_norm": 0.05738500505685806,
|
1148 |
+
"learning_rate": 0.00010866666666666666,
|
1149 |
+
"loss": 1.42,
|
1150 |
+
"step": 7350
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 580.3921568627451,
|
1154 |
+
"grad_norm": 0.06691340357065201,
|
1155 |
+
"learning_rate": 0.00010033333333333334,
|
1156 |
+
"loss": 1.4185,
|
1157 |
+
"step": 7400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 584.3137254901961,
|
1161 |
+
"grad_norm": 0.06185409054160118,
|
1162 |
+
"learning_rate": 9.2e-05,
|
1163 |
+
"loss": 1.4172,
|
1164 |
+
"step": 7450
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 588.2352941176471,
|
1168 |
+
"grad_norm": 0.14216652512550354,
|
1169 |
+
"learning_rate": 8.366666666666666e-05,
|
1170 |
+
"loss": 1.4194,
|
1171 |
+
"step": 7500
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 588.2352941176471,
|
1175 |
+
"eval_loss": 1.4361063241958618,
|
1176 |
+
"eval_runtime": 6.733,
|
1177 |
+
"eval_samples_per_second": 26.734,
|
1178 |
+
"eval_steps_per_second": 3.416,
|
1179 |
+
"step": 7500
|
1180 |
}
|
1181 |
],
|
1182 |
"logging_steps": 50,
|
|
|
1196 |
"attributes": {}
|
1197 |
}
|
1198 |
},
|
1199 |
+
"total_flos": 1.631701918768069e+17,
|
1200 |
"train_batch_size": 32,
|
1201 |
"trial_name": null,
|
1202 |
"trial_params": null
|