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 231448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0da31e174f14b582413d238f092823f82409ac74e15fa6e4c1e6206e1b1560f
|
| 3 |
size 231448
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 254576
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b359f1f4456fc66e8af7bd6af10b44ef389cdde081cd3d67e2b08e1b3e921f33
|
| 3 |
size 254576
|
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 sha256:611fca5a82812c7bf7c0a091240a103959a433ead0308056e898bc62b8c9fbdd
|
| 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:d5a2d44d83e73859366b99e73d612be6557265dcc5de9f969cbf19f618c3c8ce
|
| 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:e8279a5d0480e72cd82abac26ef8bbb4b3ea84e29cd00bb2e8cb04037ecdb6dc
|
| 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:bae1f2d1b05a13e3d9d7174173a91262a36a0116d043a0090d590a0b0222d664
|
| 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:c869cce088ba4dd9dfd0f0e58d0da60479fc388bc53e70941b100ddad2afc086
|
| 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 sha256:61fc0ca314c33e82c0809352bc2be36cc8b5692e46265c358b2f4772a328143d
|
| 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:b77c83b6bdd0d80895f4e0994d6455635cada32b7bb73ad8d3d964e4a7615606
|
| 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 sha256:8aeb1aa09d0638b89c02d026f94ae7283dea7fac42be93be421d08bbc2804afc
|
| 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": 10.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 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": 3362.23,
|
| 1090 |
"eval_steps_per_second": 105.118,
|
| 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": 10.308185577392578,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.07262823422605538,
|
| 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": 3362.23,
|
| 1090 |
"eval_steps_per_second": 105.118,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.05483431684067181,
|
| 1095 |
+
"grad_norm": 0.09872455149888992,
|
| 1096 |
+
"learning_rate": 2.6047368421052634e-05,
|
| 1097 |
+
"loss": 10.2997,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.055197458011802085,
|
| 1102 |
+
"grad_norm": 0.06669897586107254,
|
| 1103 |
+
"learning_rate": 2.5515789473684213e-05,
|
| 1104 |
+
"loss": 10.3051,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.055560599182932366,
|
| 1109 |
+
"grad_norm": 0.05202397704124451,
|
| 1110 |
+
"learning_rate": 2.4984210526315788e-05,
|
| 1111 |
+
"loss": 10.3089,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.05592374035406264,
|
| 1116 |
+
"grad_norm": 0.05739379674196243,
|
| 1117 |
+
"learning_rate": 2.445263157894737e-05,
|
| 1118 |
+
"loss": 10.3133,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.05628688152519292,
|
| 1123 |
+
"grad_norm": 0.07251626998186111,
|
| 1124 |
+
"learning_rate": 2.3921052631578946e-05,
|
| 1125 |
+
"loss": 10.3164,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.056650022696323195,
|
| 1130 |
+
"grad_norm": 0.09823988378047943,
|
| 1131 |
+
"learning_rate": 2.3389473684210528e-05,
|
| 1132 |
+
"loss": 10.3158,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.057013163867453476,
|
| 1137 |
+
"grad_norm": 0.1004052385687828,
|
| 1138 |
+
"learning_rate": 2.2857894736842106e-05,
|
| 1139 |
+
"loss": 10.296,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.05737630503858375,
|
| 1144 |
+
"grad_norm": 0.0734814703464508,
|
| 1145 |
+
"learning_rate": 2.2326315789473685e-05,
|
| 1146 |
+
"loss": 10.3039,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.057739446209714024,
|
| 1151 |
+
"grad_norm": 0.04906293377280235,
|
| 1152 |
+
"learning_rate": 2.1794736842105264e-05,
|
| 1153 |
+
"loss": 10.3087,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.058102587380844305,
|
| 1158 |
+
"grad_norm": 0.053951047360897064,
|
| 1159 |
+
"learning_rate": 2.1263157894736842e-05,
|
| 1160 |
+
"loss": 10.3102,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.05846572855197458,
|
| 1165 |
+
"grad_norm": 0.07190736383199692,
|
| 1166 |
+
"learning_rate": 2.073157894736842e-05,
|
| 1167 |
+
"loss": 10.3167,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.05882886972310486,
|
| 1172 |
+
"grad_norm": 0.09854470193386078,
|
| 1173 |
+
"learning_rate": 2.0200000000000003e-05,
|
| 1174 |
+
"loss": 10.3165,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.059192010894235134,
|
| 1179 |
+
"grad_norm": 0.07515429705381393,
|
| 1180 |
+
"learning_rate": 1.966842105263158e-05,
|
| 1181 |
+
"loss": 10.3002,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.05955515206536541,
|
| 1186 |
+
"grad_norm": 0.06888720393180847,
|
| 1187 |
+
"learning_rate": 1.913684210526316e-05,
|
| 1188 |
+
"loss": 10.3024,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.05991829323649569,
|
| 1193 |
+
"grad_norm": 0.054647717624902725,
|
| 1194 |
+
"learning_rate": 1.8605263157894736e-05,
|
| 1195 |
+
"loss": 10.3061,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.06028143440762596,
|
| 1200 |
+
"grad_norm": 0.05850168317556381,
|
| 1201 |
+
"learning_rate": 1.8073684210526318e-05,
|
| 1202 |
+
"loss": 10.3109,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.060644575578756243,
|
| 1207 |
+
"grad_norm": 0.05970611050724983,
|
| 1208 |
+
"learning_rate": 1.7542105263157897e-05,
|
| 1209 |
+
"loss": 10.3116,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.06100771674988652,
|
| 1214 |
+
"grad_norm": 0.094508096575737,
|
| 1215 |
+
"learning_rate": 1.7010526315789475e-05,
|
| 1216 |
+
"loss": 10.3123,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.0613708579210168,
|
| 1221 |
+
"grad_norm": 0.060756973922252655,
|
| 1222 |
+
"learning_rate": 1.6478947368421054e-05,
|
| 1223 |
+
"loss": 10.3036,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.06173399909214707,
|
| 1228 |
+
"grad_norm": 0.07302611321210861,
|
| 1229 |
+
"learning_rate": 1.5947368421052633e-05,
|
| 1230 |
+
"loss": 10.3019,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.062097140263277346,
|
| 1235 |
+
"grad_norm": 0.06162986904382706,
|
| 1236 |
+
"learning_rate": 1.541578947368421e-05,
|
| 1237 |
+
"loss": 10.3047,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.06246028143440763,
|
| 1242 |
+
"grad_norm": 0.05356194078922272,
|
| 1243 |
+
"learning_rate": 1.4884210526315788e-05,
|
| 1244 |
+
"loss": 10.3094,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.0628234226055379,
|
| 1249 |
+
"grad_norm": 0.06249609589576721,
|
| 1250 |
+
"learning_rate": 1.4352631578947369e-05,
|
| 1251 |
+
"loss": 10.309,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.06318656377666818,
|
| 1256 |
+
"grad_norm": 0.06981988996267319,
|
| 1257 |
+
"learning_rate": 1.3821052631578949e-05,
|
| 1258 |
+
"loss": 10.3136,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.06354970494779846,
|
| 1263 |
+
"grad_norm": 0.12152791023254395,
|
| 1264 |
+
"learning_rate": 1.3289473684210526e-05,
|
| 1265 |
+
"loss": 10.3166,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.06391284611892874,
|
| 1270 |
+
"grad_norm": 0.09238287806510925,
|
| 1271 |
+
"learning_rate": 1.2757894736842106e-05,
|
| 1272 |
+
"loss": 10.2989,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.06427598729005901,
|
| 1277 |
+
"grad_norm": 0.05485982820391655,
|
| 1278 |
+
"learning_rate": 1.2226315789473685e-05,
|
| 1279 |
+
"loss": 10.3074,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.06463912846118929,
|
| 1284 |
+
"grad_norm": 0.050571322441101074,
|
| 1285 |
+
"learning_rate": 1.1694736842105264e-05,
|
| 1286 |
+
"loss": 10.3061,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.06500226963231956,
|
| 1291 |
+
"grad_norm": 0.05679386109113693,
|
| 1292 |
+
"learning_rate": 1.1163157894736842e-05,
|
| 1293 |
+
"loss": 10.3071,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.06536541080344985,
|
| 1298 |
+
"grad_norm": 0.08567273616790771,
|
| 1299 |
+
"learning_rate": 1.0631578947368421e-05,
|
| 1300 |
+
"loss": 10.3117,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.06572855197458012,
|
| 1305 |
+
"grad_norm": 0.09831085801124573,
|
| 1306 |
+
"learning_rate": 1.0100000000000002e-05,
|
| 1307 |
+
"loss": 10.3135,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.0660916931457104,
|
| 1312 |
+
"grad_norm": 0.08691138029098511,
|
| 1313 |
+
"learning_rate": 9.56842105263158e-06,
|
| 1314 |
+
"loss": 10.2966,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.06645483431684067,
|
| 1319 |
+
"grad_norm": 0.06285746395587921,
|
| 1320 |
+
"learning_rate": 9.036842105263159e-06,
|
| 1321 |
+
"loss": 10.3026,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.06681797548797094,
|
| 1326 |
+
"grad_norm": 0.056860584765672684,
|
| 1327 |
+
"learning_rate": 8.505263157894738e-06,
|
| 1328 |
+
"loss": 10.3051,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.06718111665910123,
|
| 1333 |
+
"grad_norm": 0.056947801262140274,
|
| 1334 |
+
"learning_rate": 7.973684210526316e-06,
|
| 1335 |
+
"loss": 10.309,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.0675442578302315,
|
| 1340 |
+
"grad_norm": 0.07250034064054489,
|
| 1341 |
+
"learning_rate": 7.442105263157894e-06,
|
| 1342 |
+
"loss": 10.3137,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.06790739900136178,
|
| 1347 |
+
"grad_norm": 0.09779293835163116,
|
| 1348 |
+
"learning_rate": 6.9105263157894745e-06,
|
| 1349 |
+
"loss": 10.3132,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.06827054017249205,
|
| 1354 |
+
"grad_norm": 0.08150464296340942,
|
| 1355 |
+
"learning_rate": 6.378947368421053e-06,
|
| 1356 |
+
"loss": 10.2982,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.06863368134362233,
|
| 1361 |
+
"grad_norm": 0.06894616782665253,
|
| 1362 |
+
"learning_rate": 5.847368421052632e-06,
|
| 1363 |
+
"loss": 10.3014,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.06899682251475261,
|
| 1368 |
+
"grad_norm": 0.05844898149371147,
|
| 1369 |
+
"learning_rate": 5.315789473684211e-06,
|
| 1370 |
+
"loss": 10.3091,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.06935996368588289,
|
| 1375 |
+
"grad_norm": 0.05523189157247543,
|
| 1376 |
+
"learning_rate": 4.78421052631579e-06,
|
| 1377 |
+
"loss": 10.3084,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.06972310485701316,
|
| 1382 |
+
"grad_norm": 0.06870152801275253,
|
| 1383 |
+
"learning_rate": 4.252631578947369e-06,
|
| 1384 |
+
"loss": 10.3094,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.07008624602814344,
|
| 1389 |
+
"grad_norm": 0.08776228874921799,
|
| 1390 |
+
"learning_rate": 3.721052631578947e-06,
|
| 1391 |
+
"loss": 10.3117,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.07044938719927371,
|
| 1396 |
+
"grad_norm": 0.061438314616680145,
|
| 1397 |
+
"learning_rate": 3.1894736842105266e-06,
|
| 1398 |
+
"loss": 10.3034,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.070812528370404,
|
| 1403 |
+
"grad_norm": 0.08862266689538956,
|
| 1404 |
+
"learning_rate": 2.6578947368421053e-06,
|
| 1405 |
+
"loss": 10.2994,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.07117566954153427,
|
| 1410 |
+
"grad_norm": 0.05210663750767708,
|
| 1411 |
+
"learning_rate": 2.1263157894736844e-06,
|
| 1412 |
+
"loss": 10.3042,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.07153881071266455,
|
| 1417 |
+
"grad_norm": 0.04864677041769028,
|
| 1418 |
+
"learning_rate": 1.5947368421052633e-06,
|
| 1419 |
+
"loss": 10.3095,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.07190195188379482,
|
| 1424 |
+
"grad_norm": 0.08212526142597198,
|
| 1425 |
+
"learning_rate": 1.0631578947368422e-06,
|
| 1426 |
+
"loss": 10.315,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.07226509305492511,
|
| 1431 |
+
"grad_norm": 0.07653167098760605,
|
| 1432 |
+
"learning_rate": 5.315789473684211e-07,
|
| 1433 |
+
"loss": 10.3105,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.07262823422605538,
|
| 1438 |
+
"grad_norm": 0.14368408918380737,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 10.3169,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.07262823422605538,
|
| 1445 |
+
"eval_loss": 10.308185577392578,
|
| 1446 |
+
"eval_runtime": 11.1132,
|
| 1447 |
+
"eval_samples_per_second": 3338.635,
|
| 1448 |
+
"eval_steps_per_second": 104.38,
|
| 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": 347352702910464.0,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|