mikhail-panzo
commited on
Commit
•
c30599c
1
Parent(s):
4ca16bd
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 sha256:55dbef2e4e7913ed689dee8375c55fdf478657367c0213dc4f662c92e2532c07
|
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 sha256:4310d344d08e1b4d8a04135265c7e1212b3c9cacfe2d5d77dcb8fb7da2129ffd
|
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 sha256:012ecd1edf495661a426a7c3c4b090d5e2901f554832bf1d246a4e516cd8c109
|
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:c517c807e8c60e96ea2a00ec87951911c3e0f81982c0a86873d457f034e52fcd
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-
|
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": 30.034,
|
1178 |
"eval_steps_per_second": 3.757,
|
1179 |
"step": 7500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1180 |
}
|
1181 |
],
|
1182 |
"logging_steps": 50,
|
@@ -1196,7 +1274,7 @@
|
|
1196 |
"attributes": {}
|
1197 |
}
|
1198 |
},
|
1199 |
-
"total_flos": 1.
|
1200 |
"train_batch_size": 16,
|
1201 |
"trial_name": null,
|
1202 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.31487980484962463,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-8000",
|
4 |
+
"epoch": 13.403141361256544,
|
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": 30.034,
|
1178 |
"eval_steps_per_second": 3.757,
|
1179 |
"step": 7500
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 12.649214659685864,
|
1183 |
+
"grad_norm": 1.4210392236709595,
|
1184 |
+
"learning_rate": 4.453e-05,
|
1185 |
+
"loss": 0.3436,
|
1186 |
+
"step": 7550
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 12.732984293193716,
|
1190 |
+
"grad_norm": 1.275467038154602,
|
1191 |
+
"learning_rate": 4.4030000000000004e-05,
|
1192 |
+
"loss": 0.3453,
|
1193 |
+
"step": 7600
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 12.81675392670157,
|
1197 |
+
"grad_norm": 1.1207870244979858,
|
1198 |
+
"learning_rate": 4.3530000000000005e-05,
|
1199 |
+
"loss": 0.3438,
|
1200 |
+
"step": 7650
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 12.900523560209423,
|
1204 |
+
"grad_norm": 1.8535631895065308,
|
1205 |
+
"learning_rate": 4.3030000000000006e-05,
|
1206 |
+
"loss": 0.3442,
|
1207 |
+
"step": 7700
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 12.984293193717278,
|
1211 |
+
"grad_norm": 1.0426372289657593,
|
1212 |
+
"learning_rate": 4.253e-05,
|
1213 |
+
"loss": 0.3494,
|
1214 |
+
"step": 7750
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 13.06806282722513,
|
1218 |
+
"grad_norm": 1.3337020874023438,
|
1219 |
+
"learning_rate": 4.203e-05,
|
1220 |
+
"loss": 0.3413,
|
1221 |
+
"step": 7800
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 13.151832460732985,
|
1225 |
+
"grad_norm": 1.017905592918396,
|
1226 |
+
"learning_rate": 4.1530000000000004e-05,
|
1227 |
+
"loss": 0.3417,
|
1228 |
+
"step": 7850
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 13.235602094240837,
|
1232 |
+
"grad_norm": 1.166343331336975,
|
1233 |
+
"learning_rate": 4.103e-05,
|
1234 |
+
"loss": 0.3443,
|
1235 |
+
"step": 7900
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 13.319371727748692,
|
1239 |
+
"grad_norm": 1.4170418977737427,
|
1240 |
+
"learning_rate": 4.053e-05,
|
1241 |
+
"loss": 0.3433,
|
1242 |
+
"step": 7950
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 13.403141361256544,
|
1246 |
+
"grad_norm": 1.125741720199585,
|
1247 |
+
"learning_rate": 4.003e-05,
|
1248 |
+
"loss": 0.3422,
|
1249 |
+
"step": 8000
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 13.403141361256544,
|
1253 |
+
"eval_loss": 0.31487980484962463,
|
1254 |
+
"eval_runtime": 278.3852,
|
1255 |
+
"eval_samples_per_second": 30.494,
|
1256 |
+
"eval_steps_per_second": 3.815,
|
1257 |
+
"step": 8000
|
1258 |
}
|
1259 |
],
|
1260 |
"logging_steps": 50,
|
|
|
1274 |
"attributes": {}
|
1275 |
}
|
1276 |
},
|
1277 |
+
"total_flos": 1.4332007404692806e+17,
|
1278 |
"train_batch_size": 16,
|
1279 |
"trial_name": null,
|
1280 |
"trial_params": null
|