Training in progress, step 800, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 234681136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2809364a64b35c0d5cde9c200be9f916ec43e713ca4cb99b004942f6fe12b016
|
| 3 |
size 234681136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469516363
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6603b84995733c3c123fd03098b901e146787f48e8efa3a7b2cfa5001df10bf6
|
| 3 |
size 469516363
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dfb8359e21fdc9be973e48050f0f83da35c6f4ef563006494ede01971aef578
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d95cb2fcd6948e86339af624a28d1c1121924096b5ac15eb53417186944a3ee
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 50,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -944,6 +944,318 @@
|
|
| 944 |
"eval_samples_per_second": 5.482,
|
| 945 |
"eval_steps_per_second": 2.815,
|
| 946 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 947 |
}
|
| 948 |
],
|
| 949 |
"logging_steps": 5,
|
|
@@ -963,7 +1275,7 @@
|
|
| 963 |
"attributes": {}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
-
"total_flos":
|
| 967 |
"train_batch_size": 2,
|
| 968 |
"trial_name": null,
|
| 969 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8,
|
| 6 |
"eval_steps": 50,
|
| 7 |
+
"global_step": 800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 944 |
"eval_samples_per_second": 5.482,
|
| 945 |
"eval_steps_per_second": 2.815,
|
| 946 |
"step": 600
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.605,
|
| 950 |
+
"grad_norm": 26.125,
|
| 951 |
+
"learning_rate": 5e-05,
|
| 952 |
+
"loss": 3.0119483947753904,
|
| 953 |
+
"step": 605
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.61,
|
| 957 |
+
"grad_norm": 1.3515625,
|
| 958 |
+
"learning_rate": 5e-05,
|
| 959 |
+
"loss": 3.0221290588378906,
|
| 960 |
+
"step": 610
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.615,
|
| 964 |
+
"grad_norm": 1.328125,
|
| 965 |
+
"learning_rate": 5e-05,
|
| 966 |
+
"loss": 3.034591484069824,
|
| 967 |
+
"step": 615
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.62,
|
| 971 |
+
"grad_norm": 1.8359375,
|
| 972 |
+
"learning_rate": 5e-05,
|
| 973 |
+
"loss": 3.0486448287963865,
|
| 974 |
+
"step": 620
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.625,
|
| 978 |
+
"grad_norm": 6.125,
|
| 979 |
+
"learning_rate": 5e-05,
|
| 980 |
+
"loss": 3.0161321640014647,
|
| 981 |
+
"step": 625
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.63,
|
| 985 |
+
"grad_norm": 47.75,
|
| 986 |
+
"learning_rate": 5e-05,
|
| 987 |
+
"loss": 3.034286880493164,
|
| 988 |
+
"step": 630
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.635,
|
| 992 |
+
"grad_norm": 22.5,
|
| 993 |
+
"learning_rate": 5e-05,
|
| 994 |
+
"loss": 3.05667667388916,
|
| 995 |
+
"step": 635
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.64,
|
| 999 |
+
"grad_norm": 4.28125,
|
| 1000 |
+
"learning_rate": 5e-05,
|
| 1001 |
+
"loss": 3.0220699310302734,
|
| 1002 |
+
"step": 640
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.645,
|
| 1006 |
+
"grad_norm": 2.640625,
|
| 1007 |
+
"learning_rate": 5e-05,
|
| 1008 |
+
"loss": 2.995787811279297,
|
| 1009 |
+
"step": 645
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.65,
|
| 1013 |
+
"grad_norm": 3.140625,
|
| 1014 |
+
"learning_rate": 5e-05,
|
| 1015 |
+
"loss": 3.030243492126465,
|
| 1016 |
+
"step": 650
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.65,
|
| 1020 |
+
"eval_loss": 3.2928740978240967,
|
| 1021 |
+
"eval_runtime": 6.768,
|
| 1022 |
+
"eval_samples_per_second": 5.467,
|
| 1023 |
+
"eval_steps_per_second": 2.807,
|
| 1024 |
+
"step": 650
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.655,
|
| 1028 |
+
"grad_norm": 1.7734375,
|
| 1029 |
+
"learning_rate": 5e-05,
|
| 1030 |
+
"loss": 2.9878942489624025,
|
| 1031 |
+
"step": 655
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.66,
|
| 1035 |
+
"grad_norm": 21.75,
|
| 1036 |
+
"learning_rate": 5e-05,
|
| 1037 |
+
"loss": 3.0131813049316407,
|
| 1038 |
+
"step": 660
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.665,
|
| 1042 |
+
"grad_norm": 2.0,
|
| 1043 |
+
"learning_rate": 5e-05,
|
| 1044 |
+
"loss": 2.988085174560547,
|
| 1045 |
+
"step": 665
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.67,
|
| 1049 |
+
"grad_norm": 1.4296875,
|
| 1050 |
+
"learning_rate": 5e-05,
|
| 1051 |
+
"loss": 3.022294044494629,
|
| 1052 |
+
"step": 670
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.675,
|
| 1056 |
+
"grad_norm": 6.875,
|
| 1057 |
+
"learning_rate": 5e-05,
|
| 1058 |
+
"loss": 3.0046091079711914,
|
| 1059 |
+
"step": 675
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.68,
|
| 1063 |
+
"grad_norm": 2.875,
|
| 1064 |
+
"learning_rate": 5e-05,
|
| 1065 |
+
"loss": 3.013047981262207,
|
| 1066 |
+
"step": 680
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.685,
|
| 1070 |
+
"grad_norm": 17.0,
|
| 1071 |
+
"learning_rate": 5e-05,
|
| 1072 |
+
"loss": 2.9954095840454102,
|
| 1073 |
+
"step": 685
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.69,
|
| 1077 |
+
"grad_norm": 7.03125,
|
| 1078 |
+
"learning_rate": 5e-05,
|
| 1079 |
+
"loss": 3.004934310913086,
|
| 1080 |
+
"step": 690
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.695,
|
| 1084 |
+
"grad_norm": 1.84375,
|
| 1085 |
+
"learning_rate": 5e-05,
|
| 1086 |
+
"loss": 3.037328910827637,
|
| 1087 |
+
"step": 695
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.7,
|
| 1091 |
+
"grad_norm": 11.25,
|
| 1092 |
+
"learning_rate": 5e-05,
|
| 1093 |
+
"loss": 3.022724914550781,
|
| 1094 |
+
"step": 700
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.7,
|
| 1098 |
+
"eval_loss": 3.2860541343688965,
|
| 1099 |
+
"eval_runtime": 6.7324,
|
| 1100 |
+
"eval_samples_per_second": 5.496,
|
| 1101 |
+
"eval_steps_per_second": 2.822,
|
| 1102 |
+
"step": 700
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.705,
|
| 1106 |
+
"grad_norm": 1.7890625,
|
| 1107 |
+
"learning_rate": 5e-05,
|
| 1108 |
+
"loss": 2.9891803741455076,
|
| 1109 |
+
"step": 705
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.71,
|
| 1113 |
+
"grad_norm": 8.5,
|
| 1114 |
+
"learning_rate": 5e-05,
|
| 1115 |
+
"loss": 3.0228837966918944,
|
| 1116 |
+
"step": 710
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.715,
|
| 1120 |
+
"grad_norm": 2.171875,
|
| 1121 |
+
"learning_rate": 5e-05,
|
| 1122 |
+
"loss": 3.0380273818969727,
|
| 1123 |
+
"step": 715
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.72,
|
| 1127 |
+
"grad_norm": 1.6484375,
|
| 1128 |
+
"learning_rate": 5e-05,
|
| 1129 |
+
"loss": 3.013555335998535,
|
| 1130 |
+
"step": 720
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.725,
|
| 1134 |
+
"grad_norm": 1.3984375,
|
| 1135 |
+
"learning_rate": 5e-05,
|
| 1136 |
+
"loss": 2.9776601791381836,
|
| 1137 |
+
"step": 725
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.73,
|
| 1141 |
+
"grad_norm": 2.46875,
|
| 1142 |
+
"learning_rate": 5e-05,
|
| 1143 |
+
"loss": 3.0011289596557615,
|
| 1144 |
+
"step": 730
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.735,
|
| 1148 |
+
"grad_norm": 2.0625,
|
| 1149 |
+
"learning_rate": 5e-05,
|
| 1150 |
+
"loss": 2.99926872253418,
|
| 1151 |
+
"step": 735
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.74,
|
| 1155 |
+
"grad_norm": 3.453125,
|
| 1156 |
+
"learning_rate": 5e-05,
|
| 1157 |
+
"loss": 2.9941511154174805,
|
| 1158 |
+
"step": 740
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.745,
|
| 1162 |
+
"grad_norm": 6.625,
|
| 1163 |
+
"learning_rate": 5e-05,
|
| 1164 |
+
"loss": 3.0118370056152344,
|
| 1165 |
+
"step": 745
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.75,
|
| 1169 |
+
"grad_norm": 7.28125,
|
| 1170 |
+
"learning_rate": 5e-05,
|
| 1171 |
+
"loss": 2.9928028106689455,
|
| 1172 |
+
"step": 750
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.75,
|
| 1176 |
+
"eval_loss": 3.280454158782959,
|
| 1177 |
+
"eval_runtime": 6.7672,
|
| 1178 |
+
"eval_samples_per_second": 5.468,
|
| 1179 |
+
"eval_steps_per_second": 2.808,
|
| 1180 |
+
"step": 750
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.755,
|
| 1184 |
+
"grad_norm": 4.34375,
|
| 1185 |
+
"learning_rate": 5e-05,
|
| 1186 |
+
"loss": 3.012207794189453,
|
| 1187 |
+
"step": 755
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.76,
|
| 1191 |
+
"grad_norm": 1.6796875,
|
| 1192 |
+
"learning_rate": 5e-05,
|
| 1193 |
+
"loss": 2.9685001373291016,
|
| 1194 |
+
"step": 760
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.765,
|
| 1198 |
+
"grad_norm": 0.95703125,
|
| 1199 |
+
"learning_rate": 5e-05,
|
| 1200 |
+
"loss": 3.032526397705078,
|
| 1201 |
+
"step": 765
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.77,
|
| 1205 |
+
"grad_norm": 2.0625,
|
| 1206 |
+
"learning_rate": 5e-05,
|
| 1207 |
+
"loss": 3.018193244934082,
|
| 1208 |
+
"step": 770
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.775,
|
| 1212 |
+
"grad_norm": 160.0,
|
| 1213 |
+
"learning_rate": 5e-05,
|
| 1214 |
+
"loss": 2.9998651504516602,
|
| 1215 |
+
"step": 775
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.78,
|
| 1219 |
+
"grad_norm": 182.0,
|
| 1220 |
+
"learning_rate": 5e-05,
|
| 1221 |
+
"loss": 3.0007757186889648,
|
| 1222 |
+
"step": 780
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.785,
|
| 1226 |
+
"grad_norm": 3.03125,
|
| 1227 |
+
"learning_rate": 5e-05,
|
| 1228 |
+
"loss": 2.9936758041381837,
|
| 1229 |
+
"step": 785
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.79,
|
| 1233 |
+
"grad_norm": 3.4375,
|
| 1234 |
+
"learning_rate": 5e-05,
|
| 1235 |
+
"loss": 2.9737762451171874,
|
| 1236 |
+
"step": 790
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.795,
|
| 1240 |
+
"grad_norm": 63.5,
|
| 1241 |
+
"learning_rate": 5e-05,
|
| 1242 |
+
"loss": 3.0091293334960936,
|
| 1243 |
+
"step": 795
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.8,
|
| 1247 |
+
"grad_norm": 46.0,
|
| 1248 |
+
"learning_rate": 5e-05,
|
| 1249 |
+
"loss": 3.021886444091797,
|
| 1250 |
+
"step": 800
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.8,
|
| 1254 |
+
"eval_loss": 3.2757456302642822,
|
| 1255 |
+
"eval_runtime": 6.7253,
|
| 1256 |
+
"eval_samples_per_second": 5.502,
|
| 1257 |
+
"eval_steps_per_second": 2.825,
|
| 1258 |
+
"step": 800
|
| 1259 |
}
|
| 1260 |
],
|
| 1261 |
"logging_steps": 5,
|
|
|
|
| 1275 |
"attributes": {}
|
| 1276 |
}
|
| 1277 |
},
|
| 1278 |
+
"total_flos": 2.319320994545664e+17,
|
| 1279 |
"train_batch_size": 2,
|
| 1280 |
"trial_name": null,
|
| 1281 |
"trial_params": null
|