Commit
•
fbaedba
1
Parent(s):
c392a26
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 sha256:3bc7aeae14173576a0aebd29e684e90ad24f0513c8e659f4277017c800274d58
|
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:e262c67abf09f51a6988d2779ae3bb916ffc4796bf41409d1a4cf45d6e527474
|
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:b1a0bdb5e52391cb330bbf26b7de42f02e891fbc6b02cd43250006d07b1a1b82
|
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 sha256:053e3e9faa016c771f1e612410ff8471cd7862add0ff2bcd59dd7177245c9618
|
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,
|
@@ -1177,6 +1177,84 @@
|
|
1177 |
"eval_samples_per_second": 26.734,
|
1178 |
"eval_steps_per_second": 3.416,
|
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": 1.
|
1200 |
"train_batch_size": 32,
|
1201 |
"trial_name": null,
|
1202 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.41427454352378845,
|
3 |
"best_model_checkpoint": "mikhail_panzo/ceb_b128_le3_s8000/checkpoint-500",
|
4 |
+
"epoch": 627.4509803921569,
|
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": 26.734,
|
1178 |
"eval_steps_per_second": 3.416,
|
1179 |
"step": 7500
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 592.156862745098,
|
1183 |
+
"grad_norm": 0.027007540687918663,
|
1184 |
+
"learning_rate": 7.533333333333334e-05,
|
1185 |
+
"loss": 1.4173,
|
1186 |
+
"step": 7550
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 596.0784313725491,
|
1190 |
+
"grad_norm": 0.04154467582702637,
|
1191 |
+
"learning_rate": 6.7e-05,
|
1192 |
+
"loss": 1.4186,
|
1193 |
+
"step": 7600
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 600.0,
|
1197 |
+
"grad_norm": 0.10418181121349335,
|
1198 |
+
"learning_rate": 5.8666666666666665e-05,
|
1199 |
+
"loss": 1.4187,
|
1200 |
+
"step": 7650
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 603.9215686274509,
|
1204 |
+
"grad_norm": 0.041870325803756714,
|
1205 |
+
"learning_rate": 5.0333333333333335e-05,
|
1206 |
+
"loss": 1.4188,
|
1207 |
+
"step": 7700
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 607.843137254902,
|
1211 |
+
"grad_norm": 0.08349625766277313,
|
1212 |
+
"learning_rate": 4.2000000000000004e-05,
|
1213 |
+
"loss": 1.4191,
|
1214 |
+
"step": 7750
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 611.7647058823529,
|
1218 |
+
"grad_norm": 0.08984719216823578,
|
1219 |
+
"learning_rate": 3.366666666666667e-05,
|
1220 |
+
"loss": 1.4174,
|
1221 |
+
"step": 7800
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 615.6862745098039,
|
1225 |
+
"grad_norm": 0.028009561821818352,
|
1226 |
+
"learning_rate": 2.5333333333333334e-05,
|
1227 |
+
"loss": 1.4203,
|
1228 |
+
"step": 7850
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 619.6078431372549,
|
1232 |
+
"grad_norm": 0.025170741602778435,
|
1233 |
+
"learning_rate": 1.7000000000000003e-05,
|
1234 |
+
"loss": 1.4183,
|
1235 |
+
"step": 7900
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 623.5294117647059,
|
1239 |
+
"grad_norm": 0.08974526822566986,
|
1240 |
+
"learning_rate": 8.666666666666666e-06,
|
1241 |
+
"loss": 1.4177,
|
1242 |
+
"step": 7950
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 627.4509803921569,
|
1246 |
+
"grad_norm": 0.023904943838715553,
|
1247 |
+
"learning_rate": 3.3333333333333335e-07,
|
1248 |
+
"loss": 1.4184,
|
1249 |
+
"step": 8000
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 627.4509803921569,
|
1253 |
+
"eval_loss": 1.4349356889724731,
|
1254 |
+
"eval_runtime": 6.7417,
|
1255 |
+
"eval_samples_per_second": 26.7,
|
1256 |
+
"eval_steps_per_second": 3.412,
|
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": 1.7404667537759085e+17,
|
1278 |
"train_batch_size": 32,
|
1279 |
"trial_name": null,
|
1280 |
"trial_params": null
|