Training in progress, step 2500, checkpoint
Browse files- last-checkpoint/adapter_model.bin +1 -1
- last-checkpoint/global_step2500/zero_pp_rank_0_mp_rank_00_model_states.pt +1 -1
- last-checkpoint/global_step2500/zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step2500/zero_pp_rank_1_mp_rank_00_model_states.pt +1 -1
- last-checkpoint/global_step2500/zero_pp_rank_1_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step2500/zero_pp_rank_2_mp_rank_00_model_states.pt +1 -1
- last-checkpoint/global_step2500/zero_pp_rank_2_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step2500/zero_pp_rank_3_mp_rank_00_model_states.pt +1 -1
- last-checkpoint/global_step2500/zero_pp_rank_3_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/latest +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/trainer_state.json +303 -3
last-checkpoint/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 19744138
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f93f9dbc221ce7eb2f7a986f2bdf2025a0344f7d11dda174684e2f36ab62d20
|
| 3 |
size 19744138
|
last-checkpoint/global_step2500/zero_pp_rank_0_mp_rank_00_model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6508458036
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70c46d86da91d9c6ec1531e6c6d8a2dd86b8cdba8a4a17be4fa512f40a9d78cc
|
| 3 |
size 6508458036
|
last-checkpoint/global_step2500/zero_pp_rank_0_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 29495149
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8856be1339d6883c09d0b8988ff5df8643c90607dcc44c5ee0c96e06a8012e43
|
| 3 |
size 29495149
|
last-checkpoint/global_step2500/zero_pp_rank_1_mp_rank_00_model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6508458036
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9e04d558bf61661db9da9d77c6440a377a127f675876f05975e834670b4091c
|
| 3 |
size 6508458036
|
last-checkpoint/global_step2500/zero_pp_rank_1_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 29495149
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63da6d6ff981d85554533d3c5ee6657e0556bc5f60b5bbcc79d6f4913c35e1e7
|
| 3 |
size 29495149
|
last-checkpoint/global_step2500/zero_pp_rank_2_mp_rank_00_model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6508458036
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41ed229fd122478e56a15a162611f0c5199d0fcdb8bfcef172a6ac022b363456
|
| 3 |
size 6508458036
|
last-checkpoint/global_step2500/zero_pp_rank_2_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 29495149
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a73a2b1df375f648c11537c000eb296e6e3979a807266832bc02324fcbaedf0
|
| 3 |
size 29495149
|
last-checkpoint/global_step2500/zero_pp_rank_3_mp_rank_00_model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6508458036
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:975c77957f54ac39ad043dbf7040a8ac7af3dbcbb65b33a83e89d644f4c04209
|
| 3 |
size 6508458036
|
last-checkpoint/global_step2500/zero_pp_rank_3_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 29495149
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85118289c3243a02f4b200c2b6f4344c2a014bcaa13bbf45e0d6ba2c1ab7c47d
|
| 3 |
size 29495149
|
last-checkpoint/latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step2500
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c8dec4848de85a7459619a3ee9d2272ba9c96e55d70dd5489741e08b8473bb3
|
| 3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23bab7c930535eb3f4cd9b227c386dd1d48f7c52b2fc08ce849b1269c36bd946
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3effdd25d25bd2c7d4880812b78b2b7de8af5816064ffe51585b24820d0691cb
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:059a50f85f504da39009dc3cc341f1e2fbc7dd40780b00f8ebc9bed068e45c3e
|
| 3 |
size 15024
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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,
|
|
@@ -1207,13 +1207,313 @@
|
|
| 1207 |
"learning_rate": 1e-05,
|
| 1208 |
"loss": 0.6565,
|
| 1209 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1210 |
}
|
| 1211 |
],
|
| 1212 |
"logging_steps": 10,
|
| 1213 |
"max_steps": 5000,
|
| 1214 |
"num_train_epochs": 3,
|
| 1215 |
"save_steps": 500,
|
| 1216 |
-
"total_flos":
|
| 1217 |
"trial_name": null,
|
| 1218 |
"trial_params": null
|
| 1219 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0539629005059021,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1207 |
"learning_rate": 1e-05,
|
| 1208 |
"loss": 0.6565,
|
| 1209 |
"step": 2000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.85,
|
| 1213 |
+
"learning_rate": 1e-05,
|
| 1214 |
+
"loss": 0.6263,
|
| 1215 |
+
"step": 2010
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.85,
|
| 1219 |
+
"learning_rate": 1e-05,
|
| 1220 |
+
"loss": 0.6665,
|
| 1221 |
+
"step": 2020
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.86,
|
| 1225 |
+
"learning_rate": 1e-05,
|
| 1226 |
+
"loss": 0.7087,
|
| 1227 |
+
"step": 2030
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.86,
|
| 1231 |
+
"learning_rate": 1e-05,
|
| 1232 |
+
"loss": 0.7511,
|
| 1233 |
+
"step": 2040
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.86,
|
| 1237 |
+
"learning_rate": 1e-05,
|
| 1238 |
+
"loss": 0.6708,
|
| 1239 |
+
"step": 2050
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.87,
|
| 1243 |
+
"learning_rate": 1e-05,
|
| 1244 |
+
"loss": 0.674,
|
| 1245 |
+
"step": 2060
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.87,
|
| 1249 |
+
"learning_rate": 1e-05,
|
| 1250 |
+
"loss": 0.7629,
|
| 1251 |
+
"step": 2070
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.88,
|
| 1255 |
+
"learning_rate": 1e-05,
|
| 1256 |
+
"loss": 0.623,
|
| 1257 |
+
"step": 2080
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.88,
|
| 1261 |
+
"learning_rate": 1e-05,
|
| 1262 |
+
"loss": 0.6838,
|
| 1263 |
+
"step": 2090
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.89,
|
| 1267 |
+
"learning_rate": 1e-05,
|
| 1268 |
+
"loss": 0.6836,
|
| 1269 |
+
"step": 2100
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.89,
|
| 1273 |
+
"learning_rate": 1e-05,
|
| 1274 |
+
"loss": 0.627,
|
| 1275 |
+
"step": 2110
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.89,
|
| 1279 |
+
"learning_rate": 1e-05,
|
| 1280 |
+
"loss": 0.7598,
|
| 1281 |
+
"step": 2120
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.9,
|
| 1285 |
+
"learning_rate": 1e-05,
|
| 1286 |
+
"loss": 0.7417,
|
| 1287 |
+
"step": 2130
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.9,
|
| 1291 |
+
"learning_rate": 1e-05,
|
| 1292 |
+
"loss": 0.6853,
|
| 1293 |
+
"step": 2140
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.91,
|
| 1297 |
+
"learning_rate": 1e-05,
|
| 1298 |
+
"loss": 0.6359,
|
| 1299 |
+
"step": 2150
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.91,
|
| 1303 |
+
"learning_rate": 1e-05,
|
| 1304 |
+
"loss": 0.6933,
|
| 1305 |
+
"step": 2160
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.91,
|
| 1309 |
+
"learning_rate": 1e-05,
|
| 1310 |
+
"loss": 0.742,
|
| 1311 |
+
"step": 2170
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.92,
|
| 1315 |
+
"learning_rate": 1e-05,
|
| 1316 |
+
"loss": 0.6966,
|
| 1317 |
+
"step": 2180
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.92,
|
| 1321 |
+
"learning_rate": 1e-05,
|
| 1322 |
+
"loss": 0.6848,
|
| 1323 |
+
"step": 2190
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.93,
|
| 1327 |
+
"learning_rate": 1e-05,
|
| 1328 |
+
"loss": 0.6774,
|
| 1329 |
+
"step": 2200
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.93,
|
| 1333 |
+
"learning_rate": 1e-05,
|
| 1334 |
+
"loss": 0.7237,
|
| 1335 |
+
"step": 2210
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.94,
|
| 1339 |
+
"learning_rate": 1e-05,
|
| 1340 |
+
"loss": 0.7163,
|
| 1341 |
+
"step": 2220
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.94,
|
| 1345 |
+
"learning_rate": 1e-05,
|
| 1346 |
+
"loss": 0.6856,
|
| 1347 |
+
"step": 2230
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.94,
|
| 1351 |
+
"learning_rate": 1e-05,
|
| 1352 |
+
"loss": 0.7414,
|
| 1353 |
+
"step": 2240
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.95,
|
| 1357 |
+
"learning_rate": 1e-05,
|
| 1358 |
+
"loss": 0.6774,
|
| 1359 |
+
"step": 2250
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.95,
|
| 1363 |
+
"learning_rate": 1e-05,
|
| 1364 |
+
"loss": 0.6008,
|
| 1365 |
+
"step": 2260
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.96,
|
| 1369 |
+
"learning_rate": 1e-05,
|
| 1370 |
+
"loss": 0.7281,
|
| 1371 |
+
"step": 2270
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.96,
|
| 1375 |
+
"learning_rate": 1e-05,
|
| 1376 |
+
"loss": 0.7157,
|
| 1377 |
+
"step": 2280
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.97,
|
| 1381 |
+
"learning_rate": 1e-05,
|
| 1382 |
+
"loss": 0.6478,
|
| 1383 |
+
"step": 2290
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.97,
|
| 1387 |
+
"learning_rate": 1e-05,
|
| 1388 |
+
"loss": 0.7042,
|
| 1389 |
+
"step": 2300
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.97,
|
| 1393 |
+
"learning_rate": 1e-05,
|
| 1394 |
+
"loss": 0.6797,
|
| 1395 |
+
"step": 2310
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.98,
|
| 1399 |
+
"learning_rate": 1e-05,
|
| 1400 |
+
"loss": 0.7048,
|
| 1401 |
+
"step": 2320
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.98,
|
| 1405 |
+
"learning_rate": 1e-05,
|
| 1406 |
+
"loss": 0.6199,
|
| 1407 |
+
"step": 2330
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 0.99,
|
| 1411 |
+
"learning_rate": 1e-05,
|
| 1412 |
+
"loss": 0.617,
|
| 1413 |
+
"step": 2340
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.99,
|
| 1417 |
+
"learning_rate": 1e-05,
|
| 1418 |
+
"loss": 0.658,
|
| 1419 |
+
"step": 2350
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.99,
|
| 1423 |
+
"learning_rate": 1e-05,
|
| 1424 |
+
"loss": 0.7155,
|
| 1425 |
+
"step": 2360
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.0,
|
| 1429 |
+
"learning_rate": 1e-05,
|
| 1430 |
+
"loss": 0.6392,
|
| 1431 |
+
"step": 2370
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.0,
|
| 1435 |
+
"learning_rate": 1e-05,
|
| 1436 |
+
"loss": 0.6793,
|
| 1437 |
+
"step": 2380
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.01,
|
| 1441 |
+
"learning_rate": 1e-05,
|
| 1442 |
+
"loss": 0.6842,
|
| 1443 |
+
"step": 2390
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.01,
|
| 1447 |
+
"learning_rate": 1e-05,
|
| 1448 |
+
"loss": 0.6615,
|
| 1449 |
+
"step": 2400
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.02,
|
| 1453 |
+
"learning_rate": 1e-05,
|
| 1454 |
+
"loss": 0.7222,
|
| 1455 |
+
"step": 2410
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 1.02,
|
| 1459 |
+
"learning_rate": 1e-05,
|
| 1460 |
+
"loss": 0.7035,
|
| 1461 |
+
"step": 2420
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 1.02,
|
| 1465 |
+
"learning_rate": 1e-05,
|
| 1466 |
+
"loss": 0.6866,
|
| 1467 |
+
"step": 2430
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.03,
|
| 1471 |
+
"learning_rate": 1e-05,
|
| 1472 |
+
"loss": 0.6694,
|
| 1473 |
+
"step": 2440
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.03,
|
| 1477 |
+
"learning_rate": 1e-05,
|
| 1478 |
+
"loss": 0.6687,
|
| 1479 |
+
"step": 2450
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.04,
|
| 1483 |
+
"learning_rate": 1e-05,
|
| 1484 |
+
"loss": 0.6515,
|
| 1485 |
+
"step": 2460
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.04,
|
| 1489 |
+
"learning_rate": 1e-05,
|
| 1490 |
+
"loss": 0.66,
|
| 1491 |
+
"step": 2470
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.05,
|
| 1495 |
+
"learning_rate": 1e-05,
|
| 1496 |
+
"loss": 0.6523,
|
| 1497 |
+
"step": 2480
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.05,
|
| 1501 |
+
"learning_rate": 1e-05,
|
| 1502 |
+
"loss": 0.676,
|
| 1503 |
+
"step": 2490
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 1.05,
|
| 1507 |
+
"learning_rate": 1e-05,
|
| 1508 |
+
"loss": 0.6396,
|
| 1509 |
+
"step": 2500
|
| 1510 |
}
|
| 1511 |
],
|
| 1512 |
"logging_steps": 10,
|
| 1513 |
"max_steps": 5000,
|
| 1514 |
"num_train_epochs": 3,
|
| 1515 |
"save_steps": 500,
|
| 1516 |
+
"total_flos": 628704820592640.0,
|
| 1517 |
"trial_name": null,
|
| 1518 |
"trial_params": null
|
| 1519 |
}
|