mikhail-panzo
commited on
Commit
•
0ab6e51
1
Parent(s):
eb6fc7b
Training in progress, step 8000, 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:aaa6395b004f9c2d6401ff45a67d3ff77ced4e1cca08c39aaffc9d0ab4d436d0
|
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 sha256:5d725da6d88da70a48d641b1e7244de8f6513972858c737cd255c634cc0c677d
|
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 sha256:05fba8800114836b393870e5407236cda2061438ed36a892d186b43b76973657
|
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 sha256:0aef1303f298e810b9c563fac5650fcaebc5d5e2a568db30104db374f503c826
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.39249518513679504,
|
3 |
"best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-6000",
|
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,
|
@@ -1177,6 +1177,84 @@
|
|
1177 |
"eval_samples_per_second": 26.891,
|
1178 |
"eval_steps_per_second": 3.436,
|
1179 |
"step": 7500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1180 |
}
|
1181 |
],
|
1182 |
"logging_steps": 50,
|
@@ -1191,12 +1269,12 @@
|
|
1191 |
"should_evaluate": false,
|
1192 |
"should_log": false,
|
1193 |
"should_save": true,
|
1194 |
-
"should_training_stop":
|
1195 |
},
|
1196 |
"attributes": {}
|
1197 |
}
|
1198 |
},
|
1199 |
-
"total_flos": 8.
|
1200 |
"train_batch_size": 32,
|
1201 |
"trial_name": null,
|
1202 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.39249518513679504,
|
3 |
"best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-6000",
|
4 |
+
"epoch": 313.72549019607845,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 8000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1177 |
"eval_samples_per_second": 26.891,
|
1178 |
"eval_steps_per_second": 3.436,
|
1179 |
"step": 7500
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 296.078431372549,
|
1183 |
+
"grad_norm": 0.7973820567131042,
|
1184 |
+
"learning_rate": 7.550000000000001e-07,
|
1185 |
+
"loss": 0.3954,
|
1186 |
+
"step": 7550
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 298.03921568627453,
|
1190 |
+
"grad_norm": 0.7256256341934204,
|
1191 |
+
"learning_rate": 6.716666666666668e-07,
|
1192 |
+
"loss": 0.3934,
|
1193 |
+
"step": 7600
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 300.0,
|
1197 |
+
"grad_norm": 1.1149753332138062,
|
1198 |
+
"learning_rate": 5.883333333333333e-07,
|
1199 |
+
"loss": 0.3913,
|
1200 |
+
"step": 7650
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 301.96078431372547,
|
1204 |
+
"grad_norm": 0.6526250243186951,
|
1205 |
+
"learning_rate": 5.05e-07,
|
1206 |
+
"loss": 0.391,
|
1207 |
+
"step": 7700
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 303.921568627451,
|
1211 |
+
"grad_norm": 0.8052578568458557,
|
1212 |
+
"learning_rate": 4.2166666666666667e-07,
|
1213 |
+
"loss": 0.3889,
|
1214 |
+
"step": 7750
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 305.88235294117646,
|
1218 |
+
"grad_norm": 0.7933726906776428,
|
1219 |
+
"learning_rate": 3.3833333333333336e-07,
|
1220 |
+
"loss": 0.3918,
|
1221 |
+
"step": 7800
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 307.84313725490193,
|
1225 |
+
"grad_norm": 0.7680366635322571,
|
1226 |
+
"learning_rate": 2.55e-07,
|
1227 |
+
"loss": 0.3948,
|
1228 |
+
"step": 7850
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 309.80392156862746,
|
1232 |
+
"grad_norm": 0.8762979507446289,
|
1233 |
+
"learning_rate": 1.7166666666666668e-07,
|
1234 |
+
"loss": 0.3937,
|
1235 |
+
"step": 7900
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 311.7647058823529,
|
1239 |
+
"grad_norm": 0.7918867468833923,
|
1240 |
+
"learning_rate": 8.833333333333334e-08,
|
1241 |
+
"loss": 0.3889,
|
1242 |
+
"step": 7950
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 313.72549019607845,
|
1246 |
+
"grad_norm": 0.7141278982162476,
|
1247 |
+
"learning_rate": 5e-09,
|
1248 |
+
"loss": 0.3944,
|
1249 |
+
"step": 8000
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 313.72549019607845,
|
1253 |
+
"eval_loss": 0.3929772675037384,
|
1254 |
+
"eval_runtime": 6.3752,
|
1255 |
+
"eval_samples_per_second": 28.234,
|
1256 |
+
"eval_steps_per_second": 3.608,
|
1257 |
+
"step": 8000
|
1258 |
}
|
1259 |
],
|
1260 |
"logging_steps": 50,
|
|
|
1269 |
"should_evaluate": false,
|
1270 |
"should_log": false,
|
1271 |
"should_save": true,
|
1272 |
+
"should_training_stop": true
|
1273 |
},
|
1274 |
"attributes": {}
|
1275 |
}
|
1276 |
},
|
1277 |
+
"total_flos": 8.70355911863679e+16,
|
1278 |
"train_batch_size": 32,
|
1279 |
"trial_name": null,
|
1280 |
"trial_params": null
|