Training in progress, step 200, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +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/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 147770496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daa6a5dd07b72ef9430ace44e750fcdb4b7759bb0894a8b53a989328b0f60392
|
| 3 |
size 147770496
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 295765866
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee8d3047990aa86dc0a36c1ef1cd2bb44cd433c10bb8c7e8d5f0f851a8fd47e6
|
| 3 |
size 295765866
|
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:e26f5521fc1e6154bc9e3b1f3aa7674a376b8de111db48b8d3988bf77187f582
|
| 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:fd15b1b91b4e9d24520dd50941a3a4e7796b5305fbac3c66fe134a0d0a7ca684
|
| 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:f8ec05176df7a0c2aa9818822dcf5a3c91459baab3140e17c9bffba86c07f82f
|
| 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:f70ac3e835d56a709928da1914610ebaf09c78697ec6a3898b27108602ce80de
|
| 3 |
size 15024
|
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 sha256:78f280e0e658edbdc4fcfbaf05da6eb84d8d86c74ef9e6edc7763096efc3a439
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 1.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1113,6 +1113,372 @@
|
|
| 1113 |
"eval_samples_per_second": 39.35,
|
| 1114 |
"eval_steps_per_second": 10.231,
|
| 1115 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
@@ -1141,7 +1507,7 @@
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
-
"total_flos":
|
| 1145 |
"train_batch_size": 1,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.1887668371200562,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 1.7218186709712133,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1113 |
"eval_samples_per_second": 39.35,
|
| 1114 |
"eval_steps_per_second": 10.231,
|
| 1115 |
"step": 150
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.299973096583266,
|
| 1119 |
+
"grad_norm": 0.7098111510276794,
|
| 1120 |
+
"learning_rate": 8.262628577071638e-05,
|
| 1121 |
+
"loss": 0.9429,
|
| 1122 |
+
"step": 151
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.308582189938122,
|
| 1126 |
+
"grad_norm": 0.705226719379425,
|
| 1127 |
+
"learning_rate": 8.237311363287896e-05,
|
| 1128 |
+
"loss": 0.9092,
|
| 1129 |
+
"step": 152
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.3171912832929782,
|
| 1133 |
+
"grad_norm": 1.0044783353805542,
|
| 1134 |
+
"learning_rate": 8.211855863706654e-05,
|
| 1135 |
+
"loss": 1.0479,
|
| 1136 |
+
"step": 153
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.3258003766478343,
|
| 1140 |
+
"grad_norm": 1.1548088788986206,
|
| 1141 |
+
"learning_rate": 8.18626336431025e-05,
|
| 1142 |
+
"loss": 1.5881,
|
| 1143 |
+
"step": 154
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.3344094700026903,
|
| 1147 |
+
"grad_norm": 0.8297902941703796,
|
| 1148 |
+
"learning_rate": 8.160535158002092e-05,
|
| 1149 |
+
"loss": 1.1529,
|
| 1150 |
+
"step": 155
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.3430185633575464,
|
| 1154 |
+
"grad_norm": 0.9534130096435547,
|
| 1155 |
+
"learning_rate": 8.13467254454134e-05,
|
| 1156 |
+
"loss": 1.1669,
|
| 1157 |
+
"step": 156
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.3516276567124024,
|
| 1161 |
+
"grad_norm": 0.8651900291442871,
|
| 1162 |
+
"learning_rate": 8.108676830477255e-05,
|
| 1163 |
+
"loss": 1.0837,
|
| 1164 |
+
"step": 157
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.3602367500672585,
|
| 1168 |
+
"grad_norm": 0.7334545254707336,
|
| 1169 |
+
"learning_rate": 8.082549329083179e-05,
|
| 1170 |
+
"loss": 0.9547,
|
| 1171 |
+
"step": 158
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.3688458434221147,
|
| 1175 |
+
"grad_norm": 0.7457680702209473,
|
| 1176 |
+
"learning_rate": 8.056291360290201e-05,
|
| 1177 |
+
"loss": 1.0481,
|
| 1178 |
+
"step": 159
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.3774549367769706,
|
| 1182 |
+
"grad_norm": 0.6921712756156921,
|
| 1183 |
+
"learning_rate": 8.029904250620473e-05,
|
| 1184 |
+
"loss": 0.8894,
|
| 1185 |
+
"step": 160
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.3860640301318268,
|
| 1189 |
+
"grad_norm": 0.7528761625289917,
|
| 1190 |
+
"learning_rate": 8.003389333120192e-05,
|
| 1191 |
+
"loss": 0.9376,
|
| 1192 |
+
"step": 161
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.3946731234866827,
|
| 1196 |
+
"grad_norm": 0.8016011714935303,
|
| 1197 |
+
"learning_rate": 7.976747947292258e-05,
|
| 1198 |
+
"loss": 0.867,
|
| 1199 |
+
"step": 162
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.4032822168415389,
|
| 1203 |
+
"grad_norm": 0.8211402893066406,
|
| 1204 |
+
"learning_rate": 7.949981439028605e-05,
|
| 1205 |
+
"loss": 0.8881,
|
| 1206 |
+
"step": 163
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.411891310196395,
|
| 1210 |
+
"grad_norm": 0.8662030696868896,
|
| 1211 |
+
"learning_rate": 7.923091160542212e-05,
|
| 1212 |
+
"loss": 1.0727,
|
| 1213 |
+
"step": 164
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.420500403551251,
|
| 1217 |
+
"grad_norm": 0.9291104078292847,
|
| 1218 |
+
"learning_rate": 7.896078470298774e-05,
|
| 1219 |
+
"loss": 0.9085,
|
| 1220 |
+
"step": 165
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.4291094969061071,
|
| 1224 |
+
"grad_norm": 0.9801819324493408,
|
| 1225 |
+
"learning_rate": 7.868944732948101e-05,
|
| 1226 |
+
"loss": 1.1554,
|
| 1227 |
+
"step": 166
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.437718590260963,
|
| 1231 |
+
"grad_norm": 1.1721428632736206,
|
| 1232 |
+
"learning_rate": 7.841691319255154e-05,
|
| 1233 |
+
"loss": 1.363,
|
| 1234 |
+
"step": 167
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.4463276836158192,
|
| 1238 |
+
"grad_norm": 1.0181959867477417,
|
| 1239 |
+
"learning_rate": 7.814319606030803e-05,
|
| 1240 |
+
"loss": 1.135,
|
| 1241 |
+
"step": 168
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.4549367769706754,
|
| 1245 |
+
"grad_norm": 0.757427453994751,
|
| 1246 |
+
"learning_rate": 7.78683097606228e-05,
|
| 1247 |
+
"loss": 0.9332,
|
| 1248 |
+
"step": 169
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.4635458703255313,
|
| 1252 |
+
"grad_norm": 0.8897256255149841,
|
| 1253 |
+
"learning_rate": 7.759226818043309e-05,
|
| 1254 |
+
"loss": 1.0629,
|
| 1255 |
+
"step": 170
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.4721549636803875,
|
| 1259 |
+
"grad_norm": 1.0402635335922241,
|
| 1260 |
+
"learning_rate": 7.73150852650396e-05,
|
| 1261 |
+
"loss": 0.9096,
|
| 1262 |
+
"step": 171
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.4807640570352434,
|
| 1266 |
+
"grad_norm": 0.6742547750473022,
|
| 1267 |
+
"learning_rate": 7.703677501740194e-05,
|
| 1268 |
+
"loss": 0.9271,
|
| 1269 |
+
"step": 172
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.4893731503900995,
|
| 1273 |
+
"grad_norm": 0.8658159375190735,
|
| 1274 |
+
"learning_rate": 7.675735149743131e-05,
|
| 1275 |
+
"loss": 0.7919,
|
| 1276 |
+
"step": 173
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.4979822437449557,
|
| 1280 |
+
"grad_norm": 0.8262009024620056,
|
| 1281 |
+
"learning_rate": 7.647682882128002e-05,
|
| 1282 |
+
"loss": 0.9107,
|
| 1283 |
+
"step": 174
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.5065913370998116,
|
| 1287 |
+
"grad_norm": 0.6974323391914368,
|
| 1288 |
+
"learning_rate": 7.619522116062857e-05,
|
| 1289 |
+
"loss": 0.8795,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.5065913370998116,
|
| 1294 |
+
"eval_loss": 1.192854642868042,
|
| 1295 |
+
"eval_runtime": 1.2757,
|
| 1296 |
+
"eval_samples_per_second": 39.194,
|
| 1297 |
+
"eval_steps_per_second": 10.19,
|
| 1298 |
+
"step": 175
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.5152004304546678,
|
| 1302 |
+
"grad_norm": 0.8274783492088318,
|
| 1303 |
+
"learning_rate": 7.591254274196959e-05,
|
| 1304 |
+
"loss": 0.9152,
|
| 1305 |
+
"step": 176
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.5238095238095237,
|
| 1309 |
+
"grad_norm": 1.0990360975265503,
|
| 1310 |
+
"learning_rate": 7.562880784588916e-05,
|
| 1311 |
+
"loss": 0.8394,
|
| 1312 |
+
"step": 177
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.5324186171643799,
|
| 1316 |
+
"grad_norm": 0.8963367342948914,
|
| 1317 |
+
"learning_rate": 7.534403080634538e-05,
|
| 1318 |
+
"loss": 0.7276,
|
| 1319 |
+
"step": 178
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.541027710519236,
|
| 1323 |
+
"grad_norm": 1.506883978843689,
|
| 1324 |
+
"learning_rate": 7.505822600994424e-05,
|
| 1325 |
+
"loss": 1.4906,
|
| 1326 |
+
"step": 179
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.549636803874092,
|
| 1330 |
+
"grad_norm": 1.6557178497314453,
|
| 1331 |
+
"learning_rate": 7.477140789521276e-05,
|
| 1332 |
+
"loss": 1.1603,
|
| 1333 |
+
"step": 180
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.5582458972289481,
|
| 1337 |
+
"grad_norm": 0.9448726773262024,
|
| 1338 |
+
"learning_rate": 7.448359095186973e-05,
|
| 1339 |
+
"loss": 1.1379,
|
| 1340 |
+
"step": 181
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.566854990583804,
|
| 1344 |
+
"grad_norm": 0.754417359828949,
|
| 1345 |
+
"learning_rate": 7.419478972009348e-05,
|
| 1346 |
+
"loss": 1.0106,
|
| 1347 |
+
"step": 182
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.5754640839386602,
|
| 1351 |
+
"grad_norm": 0.844013512134552,
|
| 1352 |
+
"learning_rate": 7.390501878978759e-05,
|
| 1353 |
+
"loss": 0.938,
|
| 1354 |
+
"step": 183
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.5840731772935164,
|
| 1358 |
+
"grad_norm": 0.8120993971824646,
|
| 1359 |
+
"learning_rate": 7.361429279984355e-05,
|
| 1360 |
+
"loss": 0.9858,
|
| 1361 |
+
"step": 184
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.5926822706483723,
|
| 1365 |
+
"grad_norm": 0.8605924844741821,
|
| 1366 |
+
"learning_rate": 7.332262643740144e-05,
|
| 1367 |
+
"loss": 0.9036,
|
| 1368 |
+
"step": 185
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.6012913640032282,
|
| 1372 |
+
"grad_norm": 0.8876140117645264,
|
| 1373 |
+
"learning_rate": 7.303003443710784e-05,
|
| 1374 |
+
"loss": 0.8838,
|
| 1375 |
+
"step": 186
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.6099004573580844,
|
| 1379 |
+
"grad_norm": 0.9637414216995239,
|
| 1380 |
+
"learning_rate": 7.273653158037151e-05,
|
| 1381 |
+
"loss": 0.828,
|
| 1382 |
+
"step": 187
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.6185095507129406,
|
| 1386 |
+
"grad_norm": 0.8308393955230713,
|
| 1387 |
+
"learning_rate": 7.244213269461656e-05,
|
| 1388 |
+
"loss": 0.9496,
|
| 1389 |
+
"step": 188
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.6271186440677967,
|
| 1393 |
+
"grad_norm": 0.8119847178459167,
|
| 1394 |
+
"learning_rate": 7.214685265253351e-05,
|
| 1395 |
+
"loss": 0.9974,
|
| 1396 |
+
"step": 189
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.6357277374226527,
|
| 1400 |
+
"grad_norm": 0.8133478760719299,
|
| 1401 |
+
"learning_rate": 7.185070637132787e-05,
|
| 1402 |
+
"loss": 0.7914,
|
| 1403 |
+
"step": 190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.6443368307775086,
|
| 1407 |
+
"grad_norm": 1.075223445892334,
|
| 1408 |
+
"learning_rate": 7.15537088119665e-05,
|
| 1409 |
+
"loss": 1.095,
|
| 1410 |
+
"step": 191
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.6529459241323647,
|
| 1414 |
+
"grad_norm": 1.0103572607040405,
|
| 1415 |
+
"learning_rate": 7.12558749784219e-05,
|
| 1416 |
+
"loss": 1.2195,
|
| 1417 |
+
"step": 192
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.661555017487221,
|
| 1421 |
+
"grad_norm": 1.1441484689712524,
|
| 1422 |
+
"learning_rate": 7.095721991691411e-05,
|
| 1423 |
+
"loss": 1.0929,
|
| 1424 |
+
"step": 193
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.670164110842077,
|
| 1428 |
+
"grad_norm": 1.2061221599578857,
|
| 1429 |
+
"learning_rate": 7.065775871515072e-05,
|
| 1430 |
+
"loss": 1.1353,
|
| 1431 |
+
"step": 194
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.678773204196933,
|
| 1435 |
+
"grad_norm": 1.0299855470657349,
|
| 1436 |
+
"learning_rate": 7.035750650156458e-05,
|
| 1437 |
+
"loss": 1.0423,
|
| 1438 |
+
"step": 195
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.687382297551789,
|
| 1442 |
+
"grad_norm": 0.7968188524246216,
|
| 1443 |
+
"learning_rate": 7.005647844454949e-05,
|
| 1444 |
+
"loss": 1.0405,
|
| 1445 |
+
"step": 196
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.695991390906645,
|
| 1449 |
+
"grad_norm": 0.7397557497024536,
|
| 1450 |
+
"learning_rate": 6.975468975169402e-05,
|
| 1451 |
+
"loss": 0.9024,
|
| 1452 |
+
"step": 197
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.7046004842615012,
|
| 1456 |
+
"grad_norm": 0.7559933662414551,
|
| 1457 |
+
"learning_rate": 6.945215566901315e-05,
|
| 1458 |
+
"loss": 0.8593,
|
| 1459 |
+
"step": 198
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.7132095776163574,
|
| 1463 |
+
"grad_norm": 0.7246858477592468,
|
| 1464 |
+
"learning_rate": 6.914889148017809e-05,
|
| 1465 |
+
"loss": 0.9244,
|
| 1466 |
+
"step": 199
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.7218186709712133,
|
| 1470 |
+
"grad_norm": 0.6950869560241699,
|
| 1471 |
+
"learning_rate": 6.884491250574415e-05,
|
| 1472 |
+
"loss": 0.797,
|
| 1473 |
+
"step": 200
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.7218186709712133,
|
| 1477 |
+
"eval_loss": 1.1887668371200562,
|
| 1478 |
+
"eval_runtime": 1.2738,
|
| 1479 |
+
"eval_samples_per_second": 39.253,
|
| 1480 |
+
"eval_steps_per_second": 10.206,
|
| 1481 |
+
"step": 200
|
| 1482 |
}
|
| 1483 |
],
|
| 1484 |
"logging_steps": 1,
|
|
|
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
+
"total_flos": 4.248409672001782e+17,
|
| 1511 |
"train_batch_size": 1,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|