mikhail-panzo
commited on
Commit
•
3ffba78
1
Parent(s):
d1dc24e
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 sha256:14347b694edbac48f71cf8408ac46afe84e4750316570c1ed940bf72283d84fe
|
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 sha256:424e6a391353585b51b6aa2f3d9a51faefe01f643f861e61d4f4255d4be74b1e
|
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:e65d5e866573e78443e1465c9b9c0413095bd120b3384ac5fdd2285abe38197f
|
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:f11095f13a6bb8e73004d74d741982d584b499e9ac31a59ea1de9965f3fec76b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.3917270302772522,
|
3 |
"best_model_checkpoint": "mikhail-panzo/ceb_b32_le5_s8000/checkpoint-6500",
|
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": 20.184,
|
1178 |
"eval_steps_per_second": 2.579,
|
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": 4.
|
1200 |
"train_batch_size": 16,
|
1201 |
"trial_name": null,
|
1202 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.3917270302772522,
|
3 |
"best_model_checkpoint": "mikhail-panzo/ceb_b32_le5_s8000/checkpoint-6500",
|
4 |
+
"epoch": 158.41584158415841,
|
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": 20.184,
|
1178 |
"eval_steps_per_second": 2.579,
|
1179 |
"step": 7500
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 149.5049504950495,
|
1183 |
+
"grad_norm": 1.1068042516708374,
|
1184 |
+
"learning_rate": 7.566666666666667e-07,
|
1185 |
+
"loss": 0.4029,
|
1186 |
+
"step": 7550
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 150.4950495049505,
|
1190 |
+
"grad_norm": 1.2785730361938477,
|
1191 |
+
"learning_rate": 6.733333333333334e-07,
|
1192 |
+
"loss": 0.4001,
|
1193 |
+
"step": 7600
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 151.4851485148515,
|
1197 |
+
"grad_norm": 1.0063281059265137,
|
1198 |
+
"learning_rate": 5.900000000000001e-07,
|
1199 |
+
"loss": 0.3977,
|
1200 |
+
"step": 7650
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 152.47524752475246,
|
1204 |
+
"grad_norm": 1.1545789241790771,
|
1205 |
+
"learning_rate": 5.066666666666667e-07,
|
1206 |
+
"loss": 0.4015,
|
1207 |
+
"step": 7700
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 153.46534653465346,
|
1211 |
+
"grad_norm": 1.0624966621398926,
|
1212 |
+
"learning_rate": 4.233333333333334e-07,
|
1213 |
+
"loss": 0.4044,
|
1214 |
+
"step": 7750
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 154.45544554455446,
|
1218 |
+
"grad_norm": 1.3898247480392456,
|
1219 |
+
"learning_rate": 3.4000000000000003e-07,
|
1220 |
+
"loss": 0.4005,
|
1221 |
+
"step": 7800
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 155.44554455445544,
|
1225 |
+
"grad_norm": 1.2618342638015747,
|
1226 |
+
"learning_rate": 2.566666666666667e-07,
|
1227 |
+
"loss": 0.4025,
|
1228 |
+
"step": 7850
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 156.43564356435644,
|
1232 |
+
"grad_norm": 1.0798155069351196,
|
1233 |
+
"learning_rate": 1.7333333333333335e-07,
|
1234 |
+
"loss": 0.4015,
|
1235 |
+
"step": 7900
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 157.4257425742574,
|
1239 |
+
"grad_norm": 1.0550168752670288,
|
1240 |
+
"learning_rate": 9e-08,
|
1241 |
+
"loss": 0.3952,
|
1242 |
+
"step": 7950
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 158.41584158415841,
|
1246 |
+
"grad_norm": 1.0714497566223145,
|
1247 |
+
"learning_rate": 6.666666666666667e-09,
|
1248 |
+
"loss": 0.3989,
|
1249 |
+
"step": 8000
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 158.41584158415841,
|
1253 |
+
"eval_loss": 0.39282524585723877,
|
1254 |
+
"eval_runtime": 8.2483,
|
1255 |
+
"eval_samples_per_second": 21.823,
|
1256 |
+
"eval_steps_per_second": 2.788,
|
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": 4.322114324975938e+16,
|
1278 |
"train_batch_size": 16,
|
1279 |
"trial_name": null,
|
1280 |
"trial_params": null
|