mikhail-panzo
commited on
Commit
•
cd7e131
1
Parent(s):
9875021
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 sha256:19d39dd9b619e7904c8275e5a7874baf72c3427e4b764352c5067cc1dc59a128
|
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 sha256:8a1a37f6fef4cd1464be2db04f3bc671ccf5a3e73428f31b9491f9b4dc67ed18
|
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:f45a2e53597446c67d3516e0bd9849a98838c2b4c8578d3fd4ef0a27339ff153
|
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": 0.402925044298172,
|
3 |
"best_model_checkpoint": "mikhail-panzo/fil_b128_le5_s8000/checkpoint-4500",
|
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": 12.215,
|
1178 |
"eval_steps_per_second": 1.593,
|
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": 0.402925044298172,
|
3 |
"best_model_checkpoint": "mikhail-panzo/fil_b128_le5_s8000/checkpoint-4500",
|
4 |
+
"epoch": 695.6521739130435,
|
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": 12.215,
|
1178 |
"eval_steps_per_second": 1.593,
|
1179 |
"step": 7500
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 656.5217391304348,
|
1183 |
+
"grad_norm": 0.6540374159812927,
|
1184 |
+
"learning_rate": 7.550000000000001e-07,
|
1185 |
+
"loss": 0.4029,
|
1186 |
+
"step": 7550
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 660.8695652173913,
|
1190 |
+
"grad_norm": 0.618146538734436,
|
1191 |
+
"learning_rate": 6.716666666666668e-07,
|
1192 |
+
"loss": 0.4018,
|
1193 |
+
"step": 7600
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 665.2173913043479,
|
1197 |
+
"grad_norm": 0.7216867804527283,
|
1198 |
+
"learning_rate": 5.883333333333333e-07,
|
1199 |
+
"loss": 0.4012,
|
1200 |
+
"step": 7650
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 669.5652173913044,
|
1204 |
+
"grad_norm": 0.6385495662689209,
|
1205 |
+
"learning_rate": 5.05e-07,
|
1206 |
+
"loss": 0.4028,
|
1207 |
+
"step": 7700
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 673.9130434782609,
|
1211 |
+
"grad_norm": 0.7671997547149658,
|
1212 |
+
"learning_rate": 4.2166666666666667e-07,
|
1213 |
+
"loss": 0.4028,
|
1214 |
+
"step": 7750
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 678.2608695652174,
|
1218 |
+
"grad_norm": 0.6697407960891724,
|
1219 |
+
"learning_rate": 3.3833333333333336e-07,
|
1220 |
+
"loss": 0.4024,
|
1221 |
+
"step": 7800
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 682.6086956521739,
|
1225 |
+
"grad_norm": 0.6977794170379639,
|
1226 |
+
"learning_rate": 2.55e-07,
|
1227 |
+
"loss": 0.3988,
|
1228 |
+
"step": 7850
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 686.9565217391304,
|
1232 |
+
"grad_norm": 0.6256734132766724,
|
1233 |
+
"learning_rate": 1.7166666666666668e-07,
|
1234 |
+
"loss": 0.3989,
|
1235 |
+
"step": 7900
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 691.304347826087,
|
1239 |
+
"grad_norm": 0.7186506390571594,
|
1240 |
+
"learning_rate": 8.833333333333334e-08,
|
1241 |
+
"loss": 0.4027,
|
1242 |
+
"step": 7950
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 695.6521739130435,
|
1246 |
+
"grad_norm": 0.7653046250343323,
|
1247 |
+
"learning_rate": 5e-09,
|
1248 |
+
"loss": 0.4042,
|
1249 |
+
"step": 8000
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 695.6521739130435,
|
1253 |
+
"eval_loss": 0.4052514135837555,
|
1254 |
+
"eval_runtime": 13.2988,
|
1255 |
+
"eval_samples_per_second": 12.106,
|
1256 |
+
"eval_steps_per_second": 1.579,
|
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": 1.9390598333064925e+17,
|
1278 |
"train_batch_size": 32,
|
1279 |
"trial_name": null,
|
1280 |
"trial_params": null
|