antonpolishko
commited on
Training in progress, epoch 3, checkpoint
Browse files- last-checkpoint/model-00001-of-00004.safetensors +1 -1
- last-checkpoint/model-00002-of-00004.safetensors +1 -1
- last-checkpoint/model-00003-of-00004.safetensors +1 -1
- last-checkpoint/model-00004-of-00004.safetensors +1 -1
- last-checkpoint/optimizer.pt +2 -2
- 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 +523 -4
last-checkpoint/model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4903351912
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44918dfe39ee4b6d085b2fd0ede145b5142b915f183672ae9f4f3a923ec9ace2
|
3 |
size 4903351912
|
last-checkpoint/model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4947570872
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1906b644e20f7418e0ff8861b4c47c96c8329cbafa385d6221bb549bd49078a6
|
3 |
size 4947570872
|
last-checkpoint/model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4962221464
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f784163add06741c32f71bfd53242b55e4499fad506d9059b5bffcf9bf06714a
|
3 |
size 4962221464
|
last-checkpoint/model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3670322200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c8c9b8ecede7d332419cd9140fecb55d03b3de4fdcc2b353e9acb041598999f
|
3 |
size 3670322200
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69d47d5b8f28bba9ccfb52093efcff4d4e0d7768a82f2cf566cfc4e6be74db24
|
3 |
+
size 33781260608
|
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 sha256:69ec6e3926fa071bede113523efa3dc6e630c3c7958c54a9ca321cf4d62ed145
|
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:f6127ee4f0c13500ec5038fce65af8f7beec63c137c7d4b7c157aa6303cf5879
|
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:da01d1c5eb2cc3a323f97c1f590d13ccfac2a4c5b1479bd378b4e643304f5a4f
|
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 sha256:49a3f04d76c0d3acc7d3dd95a04215f368f35a451ae8cba8a2fdba38cda9ca0a
|
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:df7d2c9825dba80cb544920f8cc0c72122f96514e6cd259052a8765b034393e2
|
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 sha256:6a20a42d44ff48cc162224010190e898fe28598ddad8cd1896d330a3bb1d8ec3
|
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 sha256:18ac0dc4f09f25179860561fcea7c5c8f997aabdc46a170665f9dc5a72bc27c6
|
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 sha256:6a16fcb5411ff961b47eff7378d85105fe9837e0492d19ea5ce3b7c4b77aa3b6
|
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:edc9a50bea580864bcd8cfa624a3000d833ef59c0757429ea149c48330d1c567
|
3 |
size 1064
|
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": 300,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1052,6 +1052,525 @@
|
|
1052 |
"learning_rate": 5.066342480105459e-07,
|
1053 |
"loss": 1.5082,
|
1054 |
"step": 730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1055 |
}
|
1056 |
],
|
1057 |
"logging_steps": 5,
|
@@ -1066,12 +1585,12 @@
|
|
1066 |
"should_evaluate": false,
|
1067 |
"should_log": false,
|
1068 |
"should_save": true,
|
1069 |
-
"should_training_stop":
|
1070 |
},
|
1071 |
"attributes": {}
|
1072 |
}
|
1073 |
},
|
1074 |
-
"total_flos":
|
1075 |
"train_batch_size": 8,
|
1076 |
"trial_name": null,
|
1077 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 300,
|
6 |
+
"global_step": 1098,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1052 |
"learning_rate": 5.066342480105459e-07,
|
1053 |
"loss": 1.5082,
|
1054 |
"step": 730
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 2.0081967213114753,
|
1058 |
+
"grad_norm": 1.6484375,
|
1059 |
+
"learning_rate": 4.942189840051287e-07,
|
1060 |
+
"loss": 1.5054,
|
1061 |
+
"step": 735
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 2.021857923497268,
|
1065 |
+
"grad_norm": 1.84375,
|
1066 |
+
"learning_rate": 4.819076099973152e-07,
|
1067 |
+
"loss": 1.4999,
|
1068 |
+
"step": 740
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 2.0355191256830603,
|
1072 |
+
"grad_norm": 1.6171875,
|
1073 |
+
"learning_rate": 4.697026548060528e-07,
|
1074 |
+
"loss": 1.5094,
|
1075 |
+
"step": 745
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 2.0491803278688523,
|
1079 |
+
"grad_norm": 1.703125,
|
1080 |
+
"learning_rate": 4.5760662539132077e-07,
|
1081 |
+
"loss": 1.5065,
|
1082 |
+
"step": 750
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 2.0628415300546448,
|
1086 |
+
"grad_norm": 1.921875,
|
1087 |
+
"learning_rate": 4.4562200633918943e-07,
|
1088 |
+
"loss": 1.5013,
|
1089 |
+
"step": 755
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 2.0765027322404372,
|
1093 |
+
"grad_norm": 1.625,
|
1094 |
+
"learning_rate": 4.337512593514728e-07,
|
1095 |
+
"loss": 1.5041,
|
1096 |
+
"step": 760
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 2.0901639344262297,
|
1100 |
+
"grad_norm": 1.6640625,
|
1101 |
+
"learning_rate": 4.2199682274008255e-07,
|
1102 |
+
"loss": 1.5083,
|
1103 |
+
"step": 765
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 2.1038251366120218,
|
1107 |
+
"grad_norm": 1.6171875,
|
1108 |
+
"learning_rate": 4.103611109261872e-07,
|
1109 |
+
"loss": 1.4982,
|
1110 |
+
"step": 770
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 2.1174863387978142,
|
1114 |
+
"grad_norm": 1.6328125,
|
1115 |
+
"learning_rate": 3.9884651394427625e-07,
|
1116 |
+
"loss": 1.5051,
|
1117 |
+
"step": 775
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 2.1311475409836067,
|
1121 |
+
"grad_norm": 1.671875,
|
1122 |
+
"learning_rate": 3.8745539695123577e-07,
|
1123 |
+
"loss": 1.4924,
|
1124 |
+
"step": 780
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 2.1448087431693987,
|
1128 |
+
"grad_norm": 1.65625,
|
1129 |
+
"learning_rate": 3.761900997405332e-07,
|
1130 |
+
"loss": 1.5113,
|
1131 |
+
"step": 785
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 2.158469945355191,
|
1135 |
+
"grad_norm": 1.6484375,
|
1136 |
+
"learning_rate": 3.6505293626161127e-07,
|
1137 |
+
"loss": 1.5058,
|
1138 |
+
"step": 790
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 2.1721311475409837,
|
1142 |
+
"grad_norm": 1.625,
|
1143 |
+
"learning_rate": 3.5404619414459147e-07,
|
1144 |
+
"loss": 1.5019,
|
1145 |
+
"step": 795
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 2.185792349726776,
|
1149 |
+
"grad_norm": 1.640625,
|
1150 |
+
"learning_rate": 3.4317213423038384e-07,
|
1151 |
+
"loss": 1.4948,
|
1152 |
+
"step": 800
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 2.199453551912568,
|
1156 |
+
"grad_norm": 1.625,
|
1157 |
+
"learning_rate": 3.32432990106297e-07,
|
1158 |
+
"loss": 1.5092,
|
1159 |
+
"step": 805
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 2.2131147540983607,
|
1163 |
+
"grad_norm": 1.734375,
|
1164 |
+
"learning_rate": 3.2183096764724914e-07,
|
1165 |
+
"loss": 1.5048,
|
1166 |
+
"step": 810
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 2.226775956284153,
|
1170 |
+
"grad_norm": 1.8984375,
|
1171 |
+
"learning_rate": 3.1136824456267006e-07,
|
1172 |
+
"loss": 1.5005,
|
1173 |
+
"step": 815
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 2.240437158469945,
|
1177 |
+
"grad_norm": 1.7421875,
|
1178 |
+
"learning_rate": 3.01046969949188e-07,
|
1179 |
+
"loss": 1.5097,
|
1180 |
+
"step": 820
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 2.2540983606557377,
|
1184 |
+
"grad_norm": 1.6640625,
|
1185 |
+
"learning_rate": 2.908692638491945e-07,
|
1186 |
+
"loss": 1.5054,
|
1187 |
+
"step": 825
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 2.26775956284153,
|
1191 |
+
"grad_norm": 1.65625,
|
1192 |
+
"learning_rate": 2.80837216815378e-07,
|
1193 |
+
"loss": 1.5131,
|
1194 |
+
"step": 830
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 2.281420765027322,
|
1198 |
+
"grad_norm": 1.671875,
|
1199 |
+
"learning_rate": 2.7095288948131114e-07,
|
1200 |
+
"loss": 1.4999,
|
1201 |
+
"step": 835
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 2.2950819672131146,
|
1205 |
+
"grad_norm": 1.6328125,
|
1206 |
+
"learning_rate": 2.6121831213818826e-07,
|
1207 |
+
"loss": 1.4989,
|
1208 |
+
"step": 840
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 2.308743169398907,
|
1212 |
+
"grad_norm": 1.6953125,
|
1213 |
+
"learning_rate": 2.51635484317793e-07,
|
1214 |
+
"loss": 1.495,
|
1215 |
+
"step": 845
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 2.3224043715846996,
|
1219 |
+
"grad_norm": 1.703125,
|
1220 |
+
"learning_rate": 2.4220637438178313e-07,
|
1221 |
+
"loss": 1.5125,
|
1222 |
+
"step": 850
|
1223 |
+
},
|
1224 |
+
{
|
1225 |
+
"epoch": 2.3360655737704916,
|
1226 |
+
"grad_norm": 1.703125,
|
1227 |
+
"learning_rate": 2.3293291911738078e-07,
|
1228 |
+
"loss": 1.5092,
|
1229 |
+
"step": 855
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 2.349726775956284,
|
1233 |
+
"grad_norm": 1.6640625,
|
1234 |
+
"learning_rate": 2.2381702333954433e-07,
|
1235 |
+
"loss": 1.4965,
|
1236 |
+
"step": 860
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 2.3633879781420766,
|
1240 |
+
"grad_norm": 1.6328125,
|
1241 |
+
"learning_rate": 2.148605594997115e-07,
|
1242 |
+
"loss": 1.497,
|
1243 |
+
"step": 865
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"epoch": 2.3770491803278686,
|
1247 |
+
"grad_norm": 1.765625,
|
1248 |
+
"learning_rate": 2.0606536730118763e-07,
|
1249 |
+
"loss": 1.5081,
|
1250 |
+
"step": 870
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 2.390710382513661,
|
1254 |
+
"grad_norm": 1.625,
|
1255 |
+
"learning_rate": 1.9743325332126105e-07,
|
1256 |
+
"loss": 1.5091,
|
1257 |
+
"step": 875
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 2.4043715846994536,
|
1261 |
+
"grad_norm": 1.6171875,
|
1262 |
+
"learning_rate": 1.8896599064012298e-07,
|
1263 |
+
"loss": 1.5045,
|
1264 |
+
"step": 880
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 2.418032786885246,
|
1268 |
+
"grad_norm": 1.640625,
|
1269 |
+
"learning_rate": 1.8066531847666888e-07,
|
1270 |
+
"loss": 1.5008,
|
1271 |
+
"step": 885
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 2.431693989071038,
|
1275 |
+
"grad_norm": 1.65625,
|
1276 |
+
"learning_rate": 1.7253294183125222e-07,
|
1277 |
+
"loss": 1.511,
|
1278 |
+
"step": 890
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"epoch": 2.4453551912568305,
|
1282 |
+
"grad_norm": 1.6328125,
|
1283 |
+
"learning_rate": 1.645705311354697e-07,
|
1284 |
+
"loss": 1.4998,
|
1285 |
+
"step": 895
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 2.459016393442623,
|
1289 |
+
"grad_norm": 1.65625,
|
1290 |
+
"learning_rate": 1.5677972190904621e-07,
|
1291 |
+
"loss": 1.5021,
|
1292 |
+
"step": 900
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 2.459016393442623,
|
1296 |
+
"eval_loss": 1.5163270235061646,
|
1297 |
+
"eval_runtime": 19.6134,
|
1298 |
+
"eval_samples_per_second": 36.098,
|
1299 |
+
"eval_steps_per_second": 1.173,
|
1300 |
+
"step": 900
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"epoch": 2.4726775956284155,
|
1304 |
+
"grad_norm": 1.6328125,
|
1305 |
+
"learning_rate": 1.4916211442389048e-07,
|
1306 |
+
"loss": 1.502,
|
1307 |
+
"step": 905
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 2.4863387978142075,
|
1311 |
+
"grad_norm": 1.625,
|
1312 |
+
"learning_rate": 1.4171927337539104e-07,
|
1313 |
+
"loss": 1.5012,
|
1314 |
+
"step": 910
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 2.5,
|
1318 |
+
"grad_norm": 1.640625,
|
1319 |
+
"learning_rate": 1.344527275610202e-07,
|
1320 |
+
"loss": 1.5019,
|
1321 |
+
"step": 915
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 2.5136612021857925,
|
1325 |
+
"grad_norm": 1.640625,
|
1326 |
+
"learning_rate": 1.273639695663108e-07,
|
1327 |
+
"loss": 1.5085,
|
1328 |
+
"step": 920
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 2.527322404371585,
|
1332 |
+
"grad_norm": 1.75,
|
1333 |
+
"learning_rate": 1.204544554582716e-07,
|
1334 |
+
"loss": 1.4973,
|
1335 |
+
"step": 925
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 2.540983606557377,
|
1339 |
+
"grad_norm": 1.671875,
|
1340 |
+
"learning_rate": 1.1372560448630375e-07,
|
1341 |
+
"loss": 1.5037,
|
1342 |
+
"step": 930
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 2.5546448087431695,
|
1346 |
+
"grad_norm": 1.65625,
|
1347 |
+
"learning_rate": 1.0717879879068004e-07,
|
1348 |
+
"loss": 1.5005,
|
1349 |
+
"step": 935
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 2.5683060109289615,
|
1353 |
+
"grad_norm": 1.6796875,
|
1354 |
+
"learning_rate": 1.0081538311864568e-07,
|
1355 |
+
"loss": 1.5024,
|
1356 |
+
"step": 940
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 2.581967213114754,
|
1360 |
+
"grad_norm": 1.625,
|
1361 |
+
"learning_rate": 9.463666454820118e-08,
|
1362 |
+
"loss": 1.4988,
|
1363 |
+
"step": 945
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 2.5956284153005464,
|
1367 |
+
"grad_norm": 1.625,
|
1368 |
+
"learning_rate": 8.864391221962064e-08,
|
1369 |
+
"loss": 1.5053,
|
1370 |
+
"step": 950
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 2.609289617486339,
|
1374 |
+
"grad_norm": 1.6328125,
|
1375 |
+
"learning_rate": 8.28383570747655e-08,
|
1376 |
+
"loss": 1.5044,
|
1377 |
+
"step": 955
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 2.6229508196721314,
|
1381 |
+
"grad_norm": 1.609375,
|
1382 |
+
"learning_rate": 7.722119160424112e-08,
|
1383 |
+
"loss": 1.4995,
|
1384 |
+
"step": 960
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 2.6366120218579234,
|
1388 |
+
"grad_norm": 1.640625,
|
1389 |
+
"learning_rate": 7.179356960245409e-08,
|
1390 |
+
"loss": 1.5122,
|
1391 |
+
"step": 965
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 2.650273224043716,
|
1395 |
+
"grad_norm": 1.7890625,
|
1396 |
+
"learning_rate": 6.655660593061718e-08,
|
1397 |
+
"loss": 1.5054,
|
1398 |
+
"step": 970
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 2.663934426229508,
|
1402 |
+
"grad_norm": 1.6484375,
|
1403 |
+
"learning_rate": 6.151137628775049e-08,
|
1404 |
+
"loss": 1.5108,
|
1405 |
+
"step": 975
|
1406 |
+
},
|
1407 |
+
{
|
1408 |
+
"epoch": 2.6775956284153004,
|
1409 |
+
"grad_norm": 1.609375,
|
1410 |
+
"learning_rate": 5.665891698972769e-08,
|
1411 |
+
"loss": 1.5003,
|
1412 |
+
"step": 980
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 2.691256830601093,
|
1416 |
+
"grad_norm": 1.640625,
|
1417 |
+
"learning_rate": 5.200022475641153e-08,
|
1418 |
+
"loss": 1.5015,
|
1419 |
+
"step": 985
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 2.7049180327868854,
|
1423 |
+
"grad_norm": 1.609375,
|
1424 |
+
"learning_rate": 4.75362565069225e-08,
|
1425 |
+
"loss": 1.5002,
|
1426 |
+
"step": 990
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 2.718579234972678,
|
1430 |
+
"grad_norm": 1.640625,
|
1431 |
+
"learning_rate": 4.326792916308242e-08,
|
1432 |
+
"loss": 1.5029,
|
1433 |
+
"step": 995
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 2.73224043715847,
|
1437 |
+
"grad_norm": 1.7421875,
|
1438 |
+
"learning_rate": 3.919611946107493e-08,
|
1439 |
+
"loss": 1.5068,
|
1440 |
+
"step": 1000
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 2.7459016393442623,
|
1444 |
+
"grad_norm": 1.921875,
|
1445 |
+
"learning_rate": 3.532166377135814e-08,
|
1446 |
+
"loss": 1.4961,
|
1447 |
+
"step": 1005
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 2.7595628415300544,
|
1451 |
+
"grad_norm": 1.6953125,
|
1452 |
+
"learning_rate": 3.164535792687095e-08,
|
1453 |
+
"loss": 1.5,
|
1454 |
+
"step": 1010
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 2.773224043715847,
|
1458 |
+
"grad_norm": 1.6171875,
|
1459 |
+
"learning_rate": 2.8167957059564095e-08,
|
1460 |
+
"loss": 1.5035,
|
1461 |
+
"step": 1015
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 2.7868852459016393,
|
1465 |
+
"grad_norm": 1.6484375,
|
1466 |
+
"learning_rate": 2.4890175445293147e-08,
|
1467 |
+
"loss": 1.5007,
|
1468 |
+
"step": 1020
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 2.800546448087432,
|
1472 |
+
"grad_norm": 1.6328125,
|
1473 |
+
"learning_rate": 2.1812686357101428e-08,
|
1474 |
+
"loss": 1.505,
|
1475 |
+
"step": 1025
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 2.8142076502732243,
|
1479 |
+
"grad_norm": 1.6484375,
|
1480 |
+
"learning_rate": 1.8936121926927507e-08,
|
1481 |
+
"loss": 1.5066,
|
1482 |
+
"step": 1030
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 2.8278688524590163,
|
1486 |
+
"grad_norm": 1.640625,
|
1487 |
+
"learning_rate": 1.6261073015761072e-08,
|
1488 |
+
"loss": 1.502,
|
1489 |
+
"step": 1035
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 2.841530054644809,
|
1493 |
+
"grad_norm": 1.75,
|
1494 |
+
"learning_rate": 1.3788089092277688e-08,
|
1495 |
+
"loss": 1.5016,
|
1496 |
+
"step": 1040
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 2.855191256830601,
|
1500 |
+
"grad_norm": 1.65625,
|
1501 |
+
"learning_rate": 1.1517678119975061e-08,
|
1502 |
+
"loss": 1.5024,
|
1503 |
+
"step": 1045
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 2.8688524590163933,
|
1507 |
+
"grad_norm": 1.609375,
|
1508 |
+
"learning_rate": 9.450306452834178e-09,
|
1509 |
+
"loss": 1.5,
|
1510 |
+
"step": 1050
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 2.8825136612021858,
|
1514 |
+
"grad_norm": 1.734375,
|
1515 |
+
"learning_rate": 7.586398739528932e-09,
|
1516 |
+
"loss": 1.4989,
|
1517 |
+
"step": 1055
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 2.8961748633879782,
|
1521 |
+
"grad_norm": 1.7890625,
|
1522 |
+
"learning_rate": 5.926337836199891e-09,
|
1523 |
+
"loss": 1.507,
|
1524 |
+
"step": 1060
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 2.9098360655737707,
|
1528 |
+
"grad_norm": 1.7734375,
|
1529 |
+
"learning_rate": 4.470464727814538e-09,
|
1530 |
+
"loss": 1.5119,
|
1531 |
+
"step": 1065
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 2.9234972677595628,
|
1535 |
+
"grad_norm": 1.7734375,
|
1536 |
+
"learning_rate": 3.219078458127078e-09,
|
1537 |
+
"loss": 1.5072,
|
1538 |
+
"step": 1070
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 2.9371584699453552,
|
1542 |
+
"grad_norm": 1.6328125,
|
1543 |
+
"learning_rate": 2.172436068252792e-09,
|
1544 |
+
"loss": 1.5074,
|
1545 |
+
"step": 1075
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 2.9508196721311473,
|
1549 |
+
"grad_norm": 1.6171875,
|
1550 |
+
"learning_rate": 1.330752543871161e-09,
|
1551 |
+
"loss": 1.4947,
|
1552 |
+
"step": 1080
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 2.9644808743169397,
|
1556 |
+
"grad_norm": 1.671875,
|
1557 |
+
"learning_rate": 6.942007710665221e-10,
|
1558 |
+
"loss": 1.5025,
|
1559 |
+
"step": 1085
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 2.978142076502732,
|
1563 |
+
"grad_norm": 1.6640625,
|
1564 |
+
"learning_rate": 2.6291150081603207e-10,
|
1565 |
+
"loss": 1.5014,
|
1566 |
+
"step": 1090
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 2.9918032786885247,
|
1570 |
+
"grad_norm": 1.609375,
|
1571 |
+
"learning_rate": 3.697332213348225e-11,
|
1572 |
+
"loss": 1.4964,
|
1573 |
+
"step": 1095
|
1574 |
}
|
1575 |
],
|
1576 |
"logging_steps": 5,
|
|
|
1585 |
"should_evaluate": false,
|
1586 |
"should_log": false,
|
1587 |
"should_save": true,
|
1588 |
+
"should_training_stop": true
|
1589 |
},
|
1590 |
"attributes": {}
|
1591 |
}
|
1592 |
},
|
1593 |
+
"total_flos": 7.187967826039144e+18,
|
1594 |
"train_batch_size": 8,
|
1595 |
"trial_name": null,
|
1596 |
"trial_params": null
|