mikhail-panzo
commited on
Commit
•
ef5825c
1
Parent(s):
65e60bd
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 sha256:188d0d1c582e736e2eec2d1d5382875e9492db41c1fbe88ec1c106466a2b07ec
|
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 sha256:3a712edfd21efaec231d91aaab20ede1aa0cfd4ebe31363aa2fdfa6f036773d5
|
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 sha256:3f87f712128c90495b5215cdd4ffe095bd74b9df4d54c07a1c61e31f0311ddf7
|
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 sha256:46a6ecce960b3a775d6eb50742229bab81345e6cd64cb3dc52202422c15ec1c7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.41767898201942444,
|
3 |
"best_model_checkpoint": "mikhail_panzo/fil_b64_le4_s8000/checkpoint-2000",
|
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": 21.343,
|
1100 |
"eval_steps_per_second": 2.685,
|
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": 0.41767898201942444,
|
3 |
"best_model_checkpoint": "mikhail_panzo/fil_b64_le4_s8000/checkpoint-2000",
|
4 |
+
"epoch": 333.3333333333333,
|
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": 21.343,
|
1100 |
"eval_steps_per_second": 2.685,
|
1101 |
"step": 7000
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 313.3333333333333,
|
1105 |
+
"grad_norm": 1.0152688026428223,
|
1106 |
+
"learning_rate": 1.59e-05,
|
1107 |
+
"loss": 0.349,
|
1108 |
+
"step": 7050
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 315.55555555555554,
|
1112 |
+
"grad_norm": 0.8982745409011841,
|
1113 |
+
"learning_rate": 1.5066666666666668e-05,
|
1114 |
+
"loss": 0.344,
|
1115 |
+
"step": 7100
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 317.77777777777777,
|
1119 |
+
"grad_norm": 0.6351937651634216,
|
1120 |
+
"learning_rate": 1.4233333333333335e-05,
|
1121 |
+
"loss": 0.3506,
|
1122 |
+
"step": 7150
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 320.0,
|
1126 |
+
"grad_norm": 1.3145679235458374,
|
1127 |
+
"learning_rate": 1.3400000000000002e-05,
|
1128 |
+
"loss": 0.348,
|
1129 |
+
"step": 7200
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 322.22222222222223,
|
1133 |
+
"grad_norm": 0.6973692178726196,
|
1134 |
+
"learning_rate": 1.2566666666666668e-05,
|
1135 |
+
"loss": 0.3434,
|
1136 |
+
"step": 7250
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 324.44444444444446,
|
1140 |
+
"grad_norm": 0.5259793996810913,
|
1141 |
+
"learning_rate": 1.1733333333333333e-05,
|
1142 |
+
"loss": 0.3386,
|
1143 |
+
"step": 7300
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 326.6666666666667,
|
1147 |
+
"grad_norm": 0.8734486103057861,
|
1148 |
+
"learning_rate": 1.09e-05,
|
1149 |
+
"loss": 0.3423,
|
1150 |
+
"step": 7350
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 328.8888888888889,
|
1154 |
+
"grad_norm": 0.7098037600517273,
|
1155 |
+
"learning_rate": 1.0066666666666668e-05,
|
1156 |
+
"loss": 0.3412,
|
1157 |
+
"step": 7400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 331.1111111111111,
|
1161 |
+
"grad_norm": 1.8435242176055908,
|
1162 |
+
"learning_rate": 9.233333333333334e-06,
|
1163 |
+
"loss": 0.3395,
|
1164 |
+
"step": 7450
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 333.3333333333333,
|
1168 |
+
"grad_norm": 0.5290047526359558,
|
1169 |
+
"learning_rate": 8.400000000000001e-06,
|
1170 |
+
"loss": 0.3447,
|
1171 |
+
"step": 7500
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 333.3333333333333,
|
1175 |
+
"eval_loss": 0.42537641525268555,
|
1176 |
+
"eval_runtime": 7.5684,
|
1177 |
+
"eval_samples_per_second": 21.009,
|
1178 |
+
"eval_steps_per_second": 2.643,
|
1179 |
+
"step": 7500
|
1180 |
}
|
1181 |
],
|
1182 |
"logging_steps": 50,
|
|
|
1196 |
"attributes": {}
|
1197 |
}
|
1198 |
},
|
1199 |
+
"total_flos": 1.0882778098582685e+17,
|
1200 |
"train_batch_size": 32,
|
1201 |
"trial_name": null,
|
1202 |
"trial_params": null
|