Commit
·
cbbaa1a
1
Parent(s):
a22bfcd
Training in progress, step 20000
Browse files- adapter_model.bin +1 -1
- {checkpoint-16000 → checkpoint-19000/adapter_model}/README.md +0 -0
- {checkpoint-16000 → checkpoint-19000/adapter_model}/adapter_config.json +5 -5
- {checkpoint-16000 → checkpoint-19000/adapter_model}/adapter_model.bin +1 -1
- {checkpoint-16000/adapter_model → checkpoint-20000}/README.md +0 -0
- {checkpoint-16000/adapter_model → checkpoint-20000}/adapter_config.json +5 -5
- {checkpoint-16000/adapter_model → checkpoint-20000}/adapter_model.bin +1 -1
- {checkpoint-16000 → checkpoint-20000}/optimizer.pt +1 -1
- {checkpoint-16000 → checkpoint-20000}/rng_state.pth +1 -1
- {checkpoint-16000 → checkpoint-20000}/scheduler.pt +1 -1
- {checkpoint-16000 → checkpoint-20000}/trainer_state.json +277 -5
- {checkpoint-16000 → checkpoint-20000}/training_args.bin +1 -1
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 500897101
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be1e03ed4e6123418bf0d0eb5aa75d959570f0aeb7b2fc39e2bb25599324a44b
|
| 3 |
size 500897101
|
{checkpoint-16000 → checkpoint-19000/adapter_model}/README.md
RENAMED
|
File without changes
|
{checkpoint-16000 → checkpoint-19000/adapter_model}/adapter_config.json
RENAMED
|
@@ -14,13 +14,13 @@
|
|
| 14 |
"r": 32,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
-
"v_proj",
|
| 18 |
-
"o_proj",
|
| 19 |
-
"gate_proj",
|
| 20 |
-
"k_proj",
|
| 21 |
"up_proj",
|
| 22 |
"down_proj",
|
| 23 |
-
"q_proj"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
| 26 |
}
|
|
|
|
| 14 |
"r": 32,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"up_proj",
|
| 18 |
"down_proj",
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"gate_proj",
|
| 23 |
+
"o_proj"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
| 26 |
}
|
{checkpoint-16000 → checkpoint-19000/adapter_model}/adapter_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 500897101
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb683e1ef26fb6759ee6f8f26fd71fa321318d9618b1721b67182a9ba22c4bed
|
| 3 |
size 500897101
|
{checkpoint-16000/adapter_model → checkpoint-20000}/README.md
RENAMED
|
File without changes
|
{checkpoint-16000/adapter_model → checkpoint-20000}/adapter_config.json
RENAMED
|
@@ -14,13 +14,13 @@
|
|
| 14 |
"r": 32,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
-
"v_proj",
|
| 18 |
-
"o_proj",
|
| 19 |
-
"gate_proj",
|
| 20 |
-
"k_proj",
|
| 21 |
"up_proj",
|
| 22 |
"down_proj",
|
| 23 |
-
"q_proj"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
| 26 |
}
|
|
|
|
| 14 |
"r": 32,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"up_proj",
|
| 18 |
"down_proj",
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"gate_proj",
|
| 23 |
+
"o_proj"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM"
|
| 26 |
}
|
{checkpoint-16000/adapter_model → checkpoint-20000}/adapter_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 500897101
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be1e03ed4e6123418bf0d0eb5aa75d959570f0aeb7b2fc39e2bb25599324a44b
|
| 3 |
size 500897101
|
{checkpoint-16000 → checkpoint-20000}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1001723453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:672e6e99ca3330c95b0226b42d37365aee4e2e1fd37665dc8a1baea4285d85ce
|
| 3 |
size 1001723453
|
{checkpoint-16000 → checkpoint-20000}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9379dd24f4bc7f42c02a2395c82177694b882887f5289666a7fc40b3c707700a
|
| 3 |
size 14575
|
{checkpoint-16000 → checkpoint-20000}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6540ccb807cc963275480e497de74768a480fbf46bd84a7c5eeaa24e5c7b2503
|
| 3 |
size 627
|
{checkpoint-16000 → checkpoint-20000}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./qlora-out/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1094,11 +1094,283 @@
|
|
| 1094 |
"eval_samples_per_second": 0.415,
|
| 1095 |
"eval_steps_per_second": 0.415,
|
| 1096 |
"step": 16000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1097 |
}
|
| 1098 |
],
|
| 1099 |
"max_steps": 80463,
|
| 1100 |
"num_train_epochs": 3,
|
| 1101 |
-
"total_flos":
|
| 1102 |
"trial_name": null,
|
| 1103 |
"trial_params": null
|
| 1104 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6324757933616638,
|
| 3 |
+
"best_model_checkpoint": "./qlora-out/checkpoint-20000",
|
| 4 |
+
"epoch": 0.7456843518138772,
|
| 5 |
+
"global_step": 20000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1094 |
"eval_samples_per_second": 0.415,
|
| 1095 |
"eval_steps_per_second": 0.415,
|
| 1096 |
"step": 16000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.6,
|
| 1100 |
+
"learning_rate": 0.00018090307655361701,
|
| 1101 |
+
"loss": 0.6354,
|
| 1102 |
+
"step": 16100
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6,
|
| 1106 |
+
"learning_rate": 0.00018067294467637228,
|
| 1107 |
+
"loss": 0.6349,
|
| 1108 |
+
"step": 16200
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.61,
|
| 1112 |
+
"learning_rate": 0.00018044158269290054,
|
| 1113 |
+
"loss": 0.6127,
|
| 1114 |
+
"step": 16300
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.61,
|
| 1118 |
+
"learning_rate": 0.00018020899413102412,
|
| 1119 |
+
"loss": 0.5977,
|
| 1120 |
+
"step": 16400
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.62,
|
| 1124 |
+
"learning_rate": 0.00017997518253726834,
|
| 1125 |
+
"loss": 0.6213,
|
| 1126 |
+
"step": 16500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.62,
|
| 1130 |
+
"learning_rate": 0.00017974015147680734,
|
| 1131 |
+
"loss": 0.6168,
|
| 1132 |
+
"step": 16600
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.62,
|
| 1136 |
+
"learning_rate": 0.00017950390453340978,
|
| 1137 |
+
"loss": 0.5978,
|
| 1138 |
+
"step": 16700
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.63,
|
| 1142 |
+
"learning_rate": 0.0001792664453093842,
|
| 1143 |
+
"loss": 0.6201,
|
| 1144 |
+
"step": 16800
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.63,
|
| 1148 |
+
"learning_rate": 0.000179027777425524,
|
| 1149 |
+
"loss": 0.6141,
|
| 1150 |
+
"step": 16900
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.63,
|
| 1154 |
+
"learning_rate": 0.00017878790452105245,
|
| 1155 |
+
"loss": 0.6135,
|
| 1156 |
+
"step": 17000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 0.63,
|
| 1160 |
+
"eval_loss": 0.6480616927146912,
|
| 1161 |
+
"eval_runtime": 1347.9883,
|
| 1162 |
+
"eval_samples_per_second": 0.402,
|
| 1163 |
+
"eval_steps_per_second": 0.402,
|
| 1164 |
+
"step": 17000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.64,
|
| 1168 |
+
"learning_rate": 0.0001785468302535669,
|
| 1169 |
+
"loss": 0.6363,
|
| 1170 |
+
"step": 17100
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.64,
|
| 1174 |
+
"learning_rate": 0.00017830455829898317,
|
| 1175 |
+
"loss": 0.6076,
|
| 1176 |
+
"step": 17200
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 0.65,
|
| 1180 |
+
"learning_rate": 0.00017806109235147963,
|
| 1181 |
+
"loss": 0.609,
|
| 1182 |
+
"step": 17300
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.65,
|
| 1186 |
+
"learning_rate": 0.00017781643612344058,
|
| 1187 |
+
"loss": 0.6044,
|
| 1188 |
+
"step": 17400
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.65,
|
| 1192 |
+
"learning_rate": 0.00017757059334539994,
|
| 1193 |
+
"loss": 0.6262,
|
| 1194 |
+
"step": 17500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.66,
|
| 1198 |
+
"learning_rate": 0.00017732356776598403,
|
| 1199 |
+
"loss": 0.6195,
|
| 1200 |
+
"step": 17600
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.66,
|
| 1204 |
+
"learning_rate": 0.0001770753631518548,
|
| 1205 |
+
"loss": 0.6328,
|
| 1206 |
+
"step": 17700
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.66,
|
| 1210 |
+
"learning_rate": 0.000176825983287652,
|
| 1211 |
+
"loss": 0.6028,
|
| 1212 |
+
"step": 17800
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 0.67,
|
| 1216 |
+
"learning_rate": 0.0001765754319759358,
|
| 1217 |
+
"loss": 0.6159,
|
| 1218 |
+
"step": 17900
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.67,
|
| 1222 |
+
"learning_rate": 0.0001763237130371287,
|
| 1223 |
+
"loss": 0.6169,
|
| 1224 |
+
"step": 18000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.67,
|
| 1228 |
+
"eval_loss": 0.6444052457809448,
|
| 1229 |
+
"eval_runtime": 1304.3701,
|
| 1230 |
+
"eval_samples_per_second": 0.416,
|
| 1231 |
+
"eval_steps_per_second": 0.416,
|
| 1232 |
+
"step": 18000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.67,
|
| 1236 |
+
"learning_rate": 0.0001760708303094572,
|
| 1237 |
+
"loss": 0.6183,
|
| 1238 |
+
"step": 18100
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.68,
|
| 1242 |
+
"learning_rate": 0.00017581678764889324,
|
| 1243 |
+
"loss": 0.6116,
|
| 1244 |
+
"step": 18200
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.68,
|
| 1248 |
+
"learning_rate": 0.00017556158892909567,
|
| 1249 |
+
"loss": 0.6406,
|
| 1250 |
+
"step": 18300
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.69,
|
| 1254 |
+
"learning_rate": 0.00017530523804135085,
|
| 1255 |
+
"loss": 0.6223,
|
| 1256 |
+
"step": 18400
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.69,
|
| 1260 |
+
"learning_rate": 0.00017504773889451361,
|
| 1261 |
+
"loss": 0.628,
|
| 1262 |
+
"step": 18500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.69,
|
| 1266 |
+
"learning_rate": 0.00017478909541494736,
|
| 1267 |
+
"loss": 0.6173,
|
| 1268 |
+
"step": 18600
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 0.7,
|
| 1272 |
+
"learning_rate": 0.00017452931154646444,
|
| 1273 |
+
"loss": 0.61,
|
| 1274 |
+
"step": 18700
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.7,
|
| 1278 |
+
"learning_rate": 0.00017426839125026598,
|
| 1279 |
+
"loss": 0.5959,
|
| 1280 |
+
"step": 18800
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.7,
|
| 1284 |
+
"learning_rate": 0.00017400633850488128,
|
| 1285 |
+
"loss": 0.5979,
|
| 1286 |
+
"step": 18900
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.71,
|
| 1290 |
+
"learning_rate": 0.00017374315730610745,
|
| 1291 |
+
"loss": 0.6161,
|
| 1292 |
+
"step": 19000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.71,
|
| 1296 |
+
"eval_loss": 0.6378119587898254,
|
| 1297 |
+
"eval_runtime": 1283.5987,
|
| 1298 |
+
"eval_samples_per_second": 0.422,
|
| 1299 |
+
"eval_steps_per_second": 0.422,
|
| 1300 |
+
"step": 19000
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.71,
|
| 1304 |
+
"learning_rate": 0.00017347885166694825,
|
| 1305 |
+
"loss": 0.6213,
|
| 1306 |
+
"step": 19100
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.72,
|
| 1310 |
+
"learning_rate": 0.00017321342561755297,
|
| 1311 |
+
"loss": 0.6217,
|
| 1312 |
+
"step": 19200
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.72,
|
| 1316 |
+
"learning_rate": 0.00017294688320515506,
|
| 1317 |
+
"loss": 0.6127,
|
| 1318 |
+
"step": 19300
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.72,
|
| 1322 |
+
"learning_rate": 0.00017267922849401024,
|
| 1323 |
+
"loss": 0.6145,
|
| 1324 |
+
"step": 19400
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 0.73,
|
| 1328 |
+
"learning_rate": 0.00017241046556533472,
|
| 1329 |
+
"loss": 0.5936,
|
| 1330 |
+
"step": 19500
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.73,
|
| 1334 |
+
"learning_rate": 0.0001721405985172428,
|
| 1335 |
+
"loss": 0.6273,
|
| 1336 |
+
"step": 19600
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.73,
|
| 1340 |
+
"learning_rate": 0.0001718696314646846,
|
| 1341 |
+
"loss": 0.6059,
|
| 1342 |
+
"step": 19700
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.74,
|
| 1346 |
+
"learning_rate": 0.000171597568539383,
|
| 1347 |
+
"loss": 0.5934,
|
| 1348 |
+
"step": 19800
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.74,
|
| 1352 |
+
"learning_rate": 0.000171324413889771,
|
| 1353 |
+
"loss": 0.6243,
|
| 1354 |
+
"step": 19900
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.75,
|
| 1358 |
+
"learning_rate": 0.00017105017168092808,
|
| 1359 |
+
"loss": 0.6164,
|
| 1360 |
+
"step": 20000
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.75,
|
| 1364 |
+
"eval_loss": 0.6324757933616638,
|
| 1365 |
+
"eval_runtime": 1266.6769,
|
| 1366 |
+
"eval_samples_per_second": 0.428,
|
| 1367 |
+
"eval_steps_per_second": 0.428,
|
| 1368 |
+
"step": 20000
|
| 1369 |
}
|
| 1370 |
],
|
| 1371 |
"max_steps": 80463,
|
| 1372 |
"num_train_epochs": 3,
|
| 1373 |
+
"total_flos": 5.606446667012506e+18,
|
| 1374 |
"trial_name": null,
|
| 1375 |
"trial_params": null
|
| 1376 |
}
|
{checkpoint-16000 → checkpoint-20000}/training_args.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8ca8c55b410908f1a6fb4d78d55fe6aad82bbca76ec8021e18981496f18fa70
|
| 3 |
size 4027
|