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/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +364 -6
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 201892112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f90c18631a24ae29070bdc5f6c29f82c4351d0b56b4719d4ceb39e58a1ea402c
|
| 3 |
size 201892112
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102864548
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3af10d751d5787fc719c49359aca1612fa19b869ee346b8eab3be2d5c6bba298
|
| 3 |
size 102864548
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1149f1d180fbb3f730b5645941ed82fb1e8338613990f69106ddb01968bf017c
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef668777611df2abea8c0afdfb5619ee783cb06b27c20a85ca9eae15b2076777
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f289ae8f02ca140c2832913fb2b3804667ed991c945c75a61b6457388ba1b364
|
| 3 |
size 15984
|
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 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33c5b141e3af25bfdb8afe29de6ac28d77b0b3947730e0a8d06e86f7daffe3f0
|
| 3 |
size 15984
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c20306543b6a40d37fdfe4b2bcd5cd8943f9125ba93ecafac39dbb8238a5b349
|
| 3 |
size 15984
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb75a79f057e225bfd7c60c969fe8054a02e7faaf011e58c26f9d3d97b72387c
|
| 3 |
size 15984
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d5f9f9b9b4e2f1c53b45faff5f42de27c4c7b194aaa702e59dc5384e1e8f867
|
| 3 |
size 15984
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee3230e1373b1d833bc72eacea77ea7c7d6beab79abd6ee9eb839cd62c9b8415
|
| 3 |
size 15984
|
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:ba4af3b1b4fa156d60adeec70df709d1741ac2f3147c676ab2805007313fc707
|
| 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": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1089,6 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 445.224,
|
| 1090 |
"eval_steps_per_second": 14.048,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1112,12 +1470,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos":
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.1064268350601196,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 1.6359918200408998,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 445.224,
|
| 1090 |
"eval_steps_per_second": 14.048,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.2351738241308794,
|
| 1095 |
+
"grad_norm": 0.3084206283092499,
|
| 1096 |
+
"learning_rate": 2.6047368421052634e-05,
|
| 1097 |
+
"loss": 1.1393,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.243353783231084,
|
| 1102 |
+
"grad_norm": 0.3451091945171356,
|
| 1103 |
+
"learning_rate": 2.5515789473684213e-05,
|
| 1104 |
+
"loss": 1.0733,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.2515337423312882,
|
| 1109 |
+
"grad_norm": 0.4800330400466919,
|
| 1110 |
+
"learning_rate": 2.4984210526315788e-05,
|
| 1111 |
+
"loss": 0.9746,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.259713701431493,
|
| 1116 |
+
"grad_norm": 0.28363898396492004,
|
| 1117 |
+
"learning_rate": 2.445263157894737e-05,
|
| 1118 |
+
"loss": 0.9993,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.2678936605316973,
|
| 1123 |
+
"grad_norm": 0.2769572138786316,
|
| 1124 |
+
"learning_rate": 2.3921052631578946e-05,
|
| 1125 |
+
"loss": 1.2425,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.2760736196319018,
|
| 1130 |
+
"grad_norm": 0.31170564889907837,
|
| 1131 |
+
"learning_rate": 2.3389473684210528e-05,
|
| 1132 |
+
"loss": 1.1531,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.2842535787321063,
|
| 1137 |
+
"grad_norm": 0.3111822307109833,
|
| 1138 |
+
"learning_rate": 2.2857894736842106e-05,
|
| 1139 |
+
"loss": 1.1104,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.2924335378323109,
|
| 1144 |
+
"grad_norm": 0.3201633393764496,
|
| 1145 |
+
"learning_rate": 2.2326315789473685e-05,
|
| 1146 |
+
"loss": 1.0955,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.3006134969325154,
|
| 1151 |
+
"grad_norm": 0.46167314052581787,
|
| 1152 |
+
"learning_rate": 2.1794736842105264e-05,
|
| 1153 |
+
"loss": 0.9636,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.30879345603272,
|
| 1158 |
+
"grad_norm": 0.27683043479919434,
|
| 1159 |
+
"learning_rate": 2.1263157894736842e-05,
|
| 1160 |
+
"loss": 0.7655,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.3169734151329244,
|
| 1165 |
+
"grad_norm": 0.27188408374786377,
|
| 1166 |
+
"learning_rate": 2.073157894736842e-05,
|
| 1167 |
+
"loss": 1.392,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.3251533742331287,
|
| 1172 |
+
"grad_norm": 0.2585594654083252,
|
| 1173 |
+
"learning_rate": 2.0200000000000003e-05,
|
| 1174 |
+
"loss": 1.1307,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.3333333333333333,
|
| 1179 |
+
"grad_norm": 0.2847974896430969,
|
| 1180 |
+
"learning_rate": 1.966842105263158e-05,
|
| 1181 |
+
"loss": 1.1373,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.3415132924335378,
|
| 1186 |
+
"grad_norm": 0.3326846957206726,
|
| 1187 |
+
"learning_rate": 1.913684210526316e-05,
|
| 1188 |
+
"loss": 1.1094,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.3496932515337423,
|
| 1193 |
+
"grad_norm": 0.414308100938797,
|
| 1194 |
+
"learning_rate": 1.8605263157894736e-05,
|
| 1195 |
+
"loss": 1.0777,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.3578732106339468,
|
| 1200 |
+
"grad_norm": 0.256447434425354,
|
| 1201 |
+
"learning_rate": 1.8073684210526318e-05,
|
| 1202 |
+
"loss": 0.3738,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.3660531697341514,
|
| 1207 |
+
"grad_norm": 0.37594905495643616,
|
| 1208 |
+
"learning_rate": 1.7542105263157897e-05,
|
| 1209 |
+
"loss": 1.7844,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.3742331288343559,
|
| 1214 |
+
"grad_norm": 0.26446691155433655,
|
| 1215 |
+
"learning_rate": 1.7010526315789475e-05,
|
| 1216 |
+
"loss": 1.1821,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.3824130879345602,
|
| 1221 |
+
"grad_norm": 0.28602975606918335,
|
| 1222 |
+
"learning_rate": 1.6478947368421054e-05,
|
| 1223 |
+
"loss": 1.136,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.390593047034765,
|
| 1228 |
+
"grad_norm": 0.3066179156303406,
|
| 1229 |
+
"learning_rate": 1.5947368421052633e-05,
|
| 1230 |
+
"loss": 1.0917,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 1.3987730061349692,
|
| 1235 |
+
"grad_norm": 0.36277103424072266,
|
| 1236 |
+
"learning_rate": 1.541578947368421e-05,
|
| 1237 |
+
"loss": 1.029,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.4069529652351738,
|
| 1242 |
+
"grad_norm": 0.5909006595611572,
|
| 1243 |
+
"learning_rate": 1.4884210526315788e-05,
|
| 1244 |
+
"loss": 0.9965,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 1.4151329243353783,
|
| 1249 |
+
"grad_norm": 0.27378860116004944,
|
| 1250 |
+
"learning_rate": 1.4352631578947369e-05,
|
| 1251 |
+
"loss": 1.046,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 1.4233128834355828,
|
| 1256 |
+
"grad_norm": 0.27462297677993774,
|
| 1257 |
+
"learning_rate": 1.3821052631578949e-05,
|
| 1258 |
+
"loss": 1.1454,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.4314928425357873,
|
| 1263 |
+
"grad_norm": 0.30874279141426086,
|
| 1264 |
+
"learning_rate": 1.3289473684210526e-05,
|
| 1265 |
+
"loss": 1.1412,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.4396728016359919,
|
| 1270 |
+
"grad_norm": 0.32977408170700073,
|
| 1271 |
+
"learning_rate": 1.2757894736842106e-05,
|
| 1272 |
+
"loss": 1.1705,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.4478527607361964,
|
| 1277 |
+
"grad_norm": 0.34034818410873413,
|
| 1278 |
+
"learning_rate": 1.2226315789473685e-05,
|
| 1279 |
+
"loss": 1.0703,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.4560327198364007,
|
| 1284 |
+
"grad_norm": 0.4745155870914459,
|
| 1285 |
+
"learning_rate": 1.1694736842105264e-05,
|
| 1286 |
+
"loss": 0.9726,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.4642126789366054,
|
| 1291 |
+
"grad_norm": 0.27849432826042175,
|
| 1292 |
+
"learning_rate": 1.1163157894736842e-05,
|
| 1293 |
+
"loss": 0.9766,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.4723926380368098,
|
| 1298 |
+
"grad_norm": 0.27196794748306274,
|
| 1299 |
+
"learning_rate": 1.0631578947368421e-05,
|
| 1300 |
+
"loss": 1.2388,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 1.4805725971370143,
|
| 1305 |
+
"grad_norm": 0.31034380197525024,
|
| 1306 |
+
"learning_rate": 1.0100000000000002e-05,
|
| 1307 |
+
"loss": 1.1685,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 1.4887525562372188,
|
| 1312 |
+
"grad_norm": 0.3115997016429901,
|
| 1313 |
+
"learning_rate": 9.56842105263158e-06,
|
| 1314 |
+
"loss": 1.1435,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 1.4969325153374233,
|
| 1319 |
+
"grad_norm": 0.32439979910850525,
|
| 1320 |
+
"learning_rate": 9.036842105263159e-06,
|
| 1321 |
+
"loss": 1.0664,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.5051124744376279,
|
| 1326 |
+
"grad_norm": 0.3903570771217346,
|
| 1327 |
+
"learning_rate": 8.505263157894738e-06,
|
| 1328 |
+
"loss": 0.9672,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.5132924335378322,
|
| 1333 |
+
"grad_norm": 0.26743942499160767,
|
| 1334 |
+
"learning_rate": 7.973684210526316e-06,
|
| 1335 |
+
"loss": 0.8184,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 1.521472392638037,
|
| 1340 |
+
"grad_norm": 0.2814801037311554,
|
| 1341 |
+
"learning_rate": 7.442105263157894e-06,
|
| 1342 |
+
"loss": 1.4269,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.5296523517382412,
|
| 1347 |
+
"grad_norm": 0.2944353520870209,
|
| 1348 |
+
"learning_rate": 6.9105263157894745e-06,
|
| 1349 |
+
"loss": 1.1613,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.537832310838446,
|
| 1354 |
+
"grad_norm": 0.2877986431121826,
|
| 1355 |
+
"learning_rate": 6.378947368421053e-06,
|
| 1356 |
+
"loss": 1.1157,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 1.5460122699386503,
|
| 1361 |
+
"grad_norm": 0.3185151517391205,
|
| 1362 |
+
"learning_rate": 5.847368421052632e-06,
|
| 1363 |
+
"loss": 1.1018,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.5541922290388548,
|
| 1368 |
+
"grad_norm": 0.3828582465648651,
|
| 1369 |
+
"learning_rate": 5.315789473684211e-06,
|
| 1370 |
+
"loss": 1.0647,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 1.5623721881390593,
|
| 1375 |
+
"grad_norm": 0.2693161964416504,
|
| 1376 |
+
"learning_rate": 4.78421052631579e-06,
|
| 1377 |
+
"loss": 0.3863,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.5705521472392638,
|
| 1382 |
+
"grad_norm": 0.3608343005180359,
|
| 1383 |
+
"learning_rate": 4.252631578947369e-06,
|
| 1384 |
+
"loss": 1.7925,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.5787321063394684,
|
| 1389 |
+
"grad_norm": 0.256085604429245,
|
| 1390 |
+
"learning_rate": 3.721052631578947e-06,
|
| 1391 |
+
"loss": 1.163,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.5869120654396727,
|
| 1396 |
+
"grad_norm": 0.2878038287162781,
|
| 1397 |
+
"learning_rate": 3.1894736842105266e-06,
|
| 1398 |
+
"loss": 1.1395,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.5950920245398774,
|
| 1403 |
+
"grad_norm": 0.3117595613002777,
|
| 1404 |
+
"learning_rate": 2.6578947368421053e-06,
|
| 1405 |
+
"loss": 1.0967,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.6032719836400817,
|
| 1410 |
+
"grad_norm": 0.3920280933380127,
|
| 1411 |
+
"learning_rate": 2.1263157894736844e-06,
|
| 1412 |
+
"loss": 1.0479,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.6114519427402862,
|
| 1417 |
+
"grad_norm": 0.6423859596252441,
|
| 1418 |
+
"learning_rate": 1.5947368421052633e-06,
|
| 1419 |
+
"loss": 0.92,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.6196319018404908,
|
| 1424 |
+
"grad_norm": 0.26212847232818604,
|
| 1425 |
+
"learning_rate": 1.0631578947368422e-06,
|
| 1426 |
+
"loss": 1.0363,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.6278118609406953,
|
| 1431 |
+
"grad_norm": 0.2488158792257309,
|
| 1432 |
+
"learning_rate": 5.315789473684211e-07,
|
| 1433 |
+
"loss": 1.163,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.6359918200408998,
|
| 1438 |
+
"grad_norm": 0.27570775151252747,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.1495,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 1.6359918200408998,
|
| 1445 |
+
"eval_loss": 1.1064268350601196,
|
| 1446 |
+
"eval_runtime": 3.7051,
|
| 1447 |
+
"eval_samples_per_second": 444.795,
|
| 1448 |
+
"eval_steps_per_second": 14.035,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1470 |
"should_evaluate": false,
|
| 1471 |
"should_log": false,
|
| 1472 |
"should_save": true,
|
| 1473 |
+
"should_training_stop": true
|
| 1474 |
},
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
+
"total_flos": 3.413036563955712e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|