Training in progress, step 1500, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9446744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac5c8a64c0ab83c2d761c379a2246a2a1b527485d9e6ca3902af906505086931
|
| 3 |
size 9446744
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4879947
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7ff189dbe667133c77befb63ee7a1edfa6003ef9d12584ea250122201496d73
|
| 3 |
size 4879947
|
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 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de0306e3417ea954b631b3708345453027eb0606d563ed02ac6f44b43062d77b
|
| 3 |
size 14917
|
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 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6658911e5c000a5756986f0311bc01884aab6a488b04caad451226050b401b09
|
| 3 |
size 14917
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca372268f4fa9335030c0cb7aedb6cdba75f457da50e7a4034abb1a2d0843689
|
| 3 |
size 1383
|
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:ae3874a248c143370ff82b050c4843d50a75c26dfebab3f0c39c4f64277b398a
|
| 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":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1008,6 +1008,506 @@
|
|
| 1008 |
"mean_token_accuracy": 0.6279609728604555,
|
| 1009 |
"num_tokens": 5948999.0,
|
| 1010 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1011 |
}
|
| 1012 |
],
|
| 1013 |
"logging_steps": 10,
|
|
@@ -1027,7 +1527,7 @@
|
|
| 1027 |
"attributes": {}
|
| 1028 |
}
|
| 1029 |
},
|
| 1030 |
-
"total_flos":
|
| 1031 |
"train_batch_size": 2,
|
| 1032 |
"trial_name": null,
|
| 1033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.577691811734365,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1008 |
"mean_token_accuracy": 0.6279609728604555,
|
| 1009 |
"num_tokens": 5948999.0,
|
| 1010 |
"step": 1000
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"entropy": 2.009714852273464,
|
| 1014 |
+
"epoch": 1.7358693316140124,
|
| 1015 |
+
"grad_norm": 0.6397438645362854,
|
| 1016 |
+
"learning_rate": 0.00015964,
|
| 1017 |
+
"loss": 2.1206714630126955,
|
| 1018 |
+
"mean_token_accuracy": 0.6264089956879616,
|
| 1019 |
+
"num_tokens": 6010131.0,
|
| 1020 |
+
"step": 1010
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"entropy": 1.9690447196364402,
|
| 1024 |
+
"epoch": 1.753062540296583,
|
| 1025 |
+
"grad_norm": 0.6629226803779602,
|
| 1026 |
+
"learning_rate": 0.00015924,
|
| 1027 |
+
"loss": 2.0379661560058593,
|
| 1028 |
+
"mean_token_accuracy": 0.6306859996169806,
|
| 1029 |
+
"num_tokens": 6070105.0,
|
| 1030 |
+
"step": 1020
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"entropy": 1.9761606559157372,
|
| 1034 |
+
"epoch": 1.7702557489791533,
|
| 1035 |
+
"grad_norm": 0.6340969800949097,
|
| 1036 |
+
"learning_rate": 0.00015884000000000002,
|
| 1037 |
+
"loss": 2.0979576110839844,
|
| 1038 |
+
"mean_token_accuracy": 0.6255223523825407,
|
| 1039 |
+
"num_tokens": 6129369.0,
|
| 1040 |
+
"step": 1030
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"entropy": 2.0855698764324186,
|
| 1044 |
+
"epoch": 1.7874489576617236,
|
| 1045 |
+
"grad_norm": 0.6090606451034546,
|
| 1046 |
+
"learning_rate": 0.00015844,
|
| 1047 |
+
"loss": 2.1925222396850588,
|
| 1048 |
+
"mean_token_accuracy": 0.6140031859278678,
|
| 1049 |
+
"num_tokens": 6191194.0,
|
| 1050 |
+
"step": 1040
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"entropy": 2.0149157389998438,
|
| 1054 |
+
"epoch": 1.804642166344294,
|
| 1055 |
+
"grad_norm": 0.6012734174728394,
|
| 1056 |
+
"learning_rate": 0.00015804,
|
| 1057 |
+
"loss": 2.104481506347656,
|
| 1058 |
+
"mean_token_accuracy": 0.6318388734012842,
|
| 1059 |
+
"num_tokens": 6254136.0,
|
| 1060 |
+
"step": 1050
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"entropy": 1.9774292945861816,
|
| 1064 |
+
"epoch": 1.8218353750268643,
|
| 1065 |
+
"grad_norm": 0.5775039792060852,
|
| 1066 |
+
"learning_rate": 0.00015764000000000002,
|
| 1067 |
+
"loss": 2.0788572311401365,
|
| 1068 |
+
"mean_token_accuracy": 0.6315916679799557,
|
| 1069 |
+
"num_tokens": 6311831.0,
|
| 1070 |
+
"step": 1060
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"entropy": 2.0096932500600815,
|
| 1074 |
+
"epoch": 1.839028583709435,
|
| 1075 |
+
"grad_norm": 0.6441799998283386,
|
| 1076 |
+
"learning_rate": 0.00015724,
|
| 1077 |
+
"loss": 2.067369079589844,
|
| 1078 |
+
"mean_token_accuracy": 0.6272157531231641,
|
| 1079 |
+
"num_tokens": 6368999.0,
|
| 1080 |
+
"step": 1070
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"entropy": 1.9509294107556343,
|
| 1084 |
+
"epoch": 1.856221792392005,
|
| 1085 |
+
"grad_norm": 0.7183738946914673,
|
| 1086 |
+
"learning_rate": 0.00015684,
|
| 1087 |
+
"loss": 2.046398162841797,
|
| 1088 |
+
"mean_token_accuracy": 0.6311775099486112,
|
| 1089 |
+
"num_tokens": 6426522.0,
|
| 1090 |
+
"step": 1080
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"entropy": 2.0291523337364197,
|
| 1094 |
+
"epoch": 1.8734150010745756,
|
| 1095 |
+
"grad_norm": 0.6105868816375732,
|
| 1096 |
+
"learning_rate": 0.00015644,
|
| 1097 |
+
"loss": 2.103832244873047,
|
| 1098 |
+
"mean_token_accuracy": 0.6217470221221447,
|
| 1099 |
+
"num_tokens": 6488781.0,
|
| 1100 |
+
"step": 1090
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"entropy": 1.9441853806376457,
|
| 1104 |
+
"epoch": 1.890608209757146,
|
| 1105 |
+
"grad_norm": 0.6209670901298523,
|
| 1106 |
+
"learning_rate": 0.00015604,
|
| 1107 |
+
"loss": 1.9830631256103515,
|
| 1108 |
+
"mean_token_accuracy": 0.6288409855216741,
|
| 1109 |
+
"num_tokens": 6545378.0,
|
| 1110 |
+
"step": 1100
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"entropy": 1.9924452617764472,
|
| 1114 |
+
"epoch": 1.9078014184397163,
|
| 1115 |
+
"grad_norm": 0.6691610813140869,
|
| 1116 |
+
"learning_rate": 0.00015564000000000002,
|
| 1117 |
+
"loss": 2.0985618591308595,
|
| 1118 |
+
"mean_token_accuracy": 0.6272476647049189,
|
| 1119 |
+
"num_tokens": 6605917.0,
|
| 1120 |
+
"step": 1110
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"entropy": 1.9443897798657417,
|
| 1124 |
+
"epoch": 1.9249946271222869,
|
| 1125 |
+
"grad_norm": 0.5956576466560364,
|
| 1126 |
+
"learning_rate": 0.00015524,
|
| 1127 |
+
"loss": 2.0018499374389647,
|
| 1128 |
+
"mean_token_accuracy": 0.6381504714488984,
|
| 1129 |
+
"num_tokens": 6661811.0,
|
| 1130 |
+
"step": 1120
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"entropy": 1.9805707216262818,
|
| 1134 |
+
"epoch": 1.942187835804857,
|
| 1135 |
+
"grad_norm": 0.5946056842803955,
|
| 1136 |
+
"learning_rate": 0.00015484,
|
| 1137 |
+
"loss": 2.0427513122558594,
|
| 1138 |
+
"mean_token_accuracy": 0.6258678704500198,
|
| 1139 |
+
"num_tokens": 6723336.0,
|
| 1140 |
+
"step": 1130
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"entropy": 1.9137805163860322,
|
| 1144 |
+
"epoch": 1.9593810444874276,
|
| 1145 |
+
"grad_norm": 0.6030678749084473,
|
| 1146 |
+
"learning_rate": 0.00015444000000000002,
|
| 1147 |
+
"loss": 1.9697463989257813,
|
| 1148 |
+
"mean_token_accuracy": 0.641855177283287,
|
| 1149 |
+
"num_tokens": 6781069.0,
|
| 1150 |
+
"step": 1140
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"entropy": 1.9368563026189805,
|
| 1154 |
+
"epoch": 1.9765742531699977,
|
| 1155 |
+
"grad_norm": 0.6237244009971619,
|
| 1156 |
+
"learning_rate": 0.00015404,
|
| 1157 |
+
"loss": 2.034241485595703,
|
| 1158 |
+
"mean_token_accuracy": 0.6384489141404629,
|
| 1159 |
+
"num_tokens": 6840129.0,
|
| 1160 |
+
"step": 1150
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"entropy": 1.8723769560456276,
|
| 1164 |
+
"epoch": 1.9937674618525683,
|
| 1165 |
+
"grad_norm": 0.6409602761268616,
|
| 1166 |
+
"learning_rate": 0.00015364,
|
| 1167 |
+
"loss": 1.9205358505249024,
|
| 1168 |
+
"mean_token_accuracy": 0.6437219835817813,
|
| 1169 |
+
"num_tokens": 6894472.0,
|
| 1170 |
+
"step": 1160
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"entropy": 1.8628178556244095,
|
| 1174 |
+
"epoch": 2.010315925209542,
|
| 1175 |
+
"grad_norm": 0.6614267230033875,
|
| 1176 |
+
"learning_rate": 0.00015324000000000002,
|
| 1177 |
+
"loss": 1.8996776580810546,
|
| 1178 |
+
"mean_token_accuracy": 0.6492502008165631,
|
| 1179 |
+
"num_tokens": 6952821.0,
|
| 1180 |
+
"step": 1170
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"entropy": 1.8918349608778953,
|
| 1184 |
+
"epoch": 2.0275091338921127,
|
| 1185 |
+
"grad_norm": 0.6476360559463501,
|
| 1186 |
+
"learning_rate": 0.00015284,
|
| 1187 |
+
"loss": 1.9498180389404296,
|
| 1188 |
+
"mean_token_accuracy": 0.6428254719823598,
|
| 1189 |
+
"num_tokens": 7014989.0,
|
| 1190 |
+
"step": 1180
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"entropy": 1.945443508028984,
|
| 1194 |
+
"epoch": 2.044702342574683,
|
| 1195 |
+
"grad_norm": 0.7725419402122498,
|
| 1196 |
+
"learning_rate": 0.00015244,
|
| 1197 |
+
"loss": 2.020453453063965,
|
| 1198 |
+
"mean_token_accuracy": 0.6328805617988109,
|
| 1199 |
+
"num_tokens": 7073087.0,
|
| 1200 |
+
"step": 1190
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"entropy": 2.039360311627388,
|
| 1204 |
+
"epoch": 2.0618955512572534,
|
| 1205 |
+
"grad_norm": 0.6981257200241089,
|
| 1206 |
+
"learning_rate": 0.00015204000000000001,
|
| 1207 |
+
"loss": 2.137688636779785,
|
| 1208 |
+
"mean_token_accuracy": 0.6245126206427812,
|
| 1209 |
+
"num_tokens": 7129761.0,
|
| 1210 |
+
"step": 1200
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"entropy": 1.9039745211601258,
|
| 1214 |
+
"epoch": 2.0790887599398236,
|
| 1215 |
+
"grad_norm": 0.6344786882400513,
|
| 1216 |
+
"learning_rate": 0.00015164,
|
| 1217 |
+
"loss": 1.945602798461914,
|
| 1218 |
+
"mean_token_accuracy": 0.6396142981946469,
|
| 1219 |
+
"num_tokens": 7187187.0,
|
| 1220 |
+
"step": 1210
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"entropy": 1.9067329421639443,
|
| 1224 |
+
"epoch": 2.096281968622394,
|
| 1225 |
+
"grad_norm": 0.6346563696861267,
|
| 1226 |
+
"learning_rate": 0.00015124,
|
| 1227 |
+
"loss": 1.990530014038086,
|
| 1228 |
+
"mean_token_accuracy": 0.6383092008531094,
|
| 1229 |
+
"num_tokens": 7247237.0,
|
| 1230 |
+
"step": 1220
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"entropy": 1.8649237960577012,
|
| 1234 |
+
"epoch": 2.1134751773049647,
|
| 1235 |
+
"grad_norm": 0.6211341023445129,
|
| 1236 |
+
"learning_rate": 0.00015084,
|
| 1237 |
+
"loss": 1.9000562667846679,
|
| 1238 |
+
"mean_token_accuracy": 0.6510101232677699,
|
| 1239 |
+
"num_tokens": 7301760.0,
|
| 1240 |
+
"step": 1230
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"entropy": 1.9364619553089142,
|
| 1244 |
+
"epoch": 2.130668385987535,
|
| 1245 |
+
"grad_norm": 0.6074926257133484,
|
| 1246 |
+
"learning_rate": 0.00015044,
|
| 1247 |
+
"loss": 2.0338695526123045,
|
| 1248 |
+
"mean_token_accuracy": 0.6359073251485825,
|
| 1249 |
+
"num_tokens": 7361681.0,
|
| 1250 |
+
"step": 1240
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"entropy": 1.86348085552454,
|
| 1254 |
+
"epoch": 2.1478615946701054,
|
| 1255 |
+
"grad_norm": 0.7472113370895386,
|
| 1256 |
+
"learning_rate": 0.00015004,
|
| 1257 |
+
"loss": 1.9359153747558593,
|
| 1258 |
+
"mean_token_accuracy": 0.6460991870611906,
|
| 1259 |
+
"num_tokens": 7424162.0,
|
| 1260 |
+
"step": 1250
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"entropy": 1.9580871596932412,
|
| 1264 |
+
"epoch": 2.1650548033526755,
|
| 1265 |
+
"grad_norm": 0.6993629336357117,
|
| 1266 |
+
"learning_rate": 0.00014964,
|
| 1267 |
+
"loss": 2.0203479766845702,
|
| 1268 |
+
"mean_token_accuracy": 0.630286343768239,
|
| 1269 |
+
"num_tokens": 7486191.0,
|
| 1270 |
+
"step": 1260
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"entropy": 1.9111438870429993,
|
| 1274 |
+
"epoch": 2.182248012035246,
|
| 1275 |
+
"grad_norm": 0.6560285687446594,
|
| 1276 |
+
"learning_rate": 0.00014924,
|
| 1277 |
+
"loss": 1.9584983825683593,
|
| 1278 |
+
"mean_token_accuracy": 0.6434897668659687,
|
| 1279 |
+
"num_tokens": 7544447.0,
|
| 1280 |
+
"step": 1270
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"entropy": 1.931545352935791,
|
| 1284 |
+
"epoch": 2.1994412207178167,
|
| 1285 |
+
"grad_norm": 0.6713767647743225,
|
| 1286 |
+
"learning_rate": 0.00014884,
|
| 1287 |
+
"loss": 2.106512451171875,
|
| 1288 |
+
"mean_token_accuracy": 0.6318223185837268,
|
| 1289 |
+
"num_tokens": 7604237.0,
|
| 1290 |
+
"step": 1280
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"entropy": 1.9441128447651863,
|
| 1294 |
+
"epoch": 2.216634429400387,
|
| 1295 |
+
"grad_norm": 0.6440369486808777,
|
| 1296 |
+
"learning_rate": 0.00014844,
|
| 1297 |
+
"loss": 2.0373985290527346,
|
| 1298 |
+
"mean_token_accuracy": 0.6320536743849516,
|
| 1299 |
+
"num_tokens": 7661475.0,
|
| 1300 |
+
"step": 1290
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"entropy": 1.949166515469551,
|
| 1304 |
+
"epoch": 2.2338276380829574,
|
| 1305 |
+
"grad_norm": 0.6829583644866943,
|
| 1306 |
+
"learning_rate": 0.00014804,
|
| 1307 |
+
"loss": 2.005051040649414,
|
| 1308 |
+
"mean_token_accuracy": 0.6337476786226034,
|
| 1309 |
+
"num_tokens": 7720352.0,
|
| 1310 |
+
"step": 1300
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"entropy": 1.8687394335865974,
|
| 1314 |
+
"epoch": 2.2510208467655275,
|
| 1315 |
+
"grad_norm": 0.6745384335517883,
|
| 1316 |
+
"learning_rate": 0.00014764,
|
| 1317 |
+
"loss": 1.9336997985839843,
|
| 1318 |
+
"mean_token_accuracy": 0.6435953237116336,
|
| 1319 |
+
"num_tokens": 7780071.0,
|
| 1320 |
+
"step": 1310
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"entropy": 1.8999060586094856,
|
| 1324 |
+
"epoch": 2.268214055448098,
|
| 1325 |
+
"grad_norm": 0.5983019471168518,
|
| 1326 |
+
"learning_rate": 0.00014724,
|
| 1327 |
+
"loss": 1.9348258972167969,
|
| 1328 |
+
"mean_token_accuracy": 0.6431682731956243,
|
| 1329 |
+
"num_tokens": 7839864.0,
|
| 1330 |
+
"step": 1320
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"entropy": 1.868900626897812,
|
| 1334 |
+
"epoch": 2.285407264130668,
|
| 1335 |
+
"grad_norm": 0.6673943400382996,
|
| 1336 |
+
"learning_rate": 0.00014684,
|
| 1337 |
+
"loss": 1.9038555145263671,
|
| 1338 |
+
"mean_token_accuracy": 0.6503972858190536,
|
| 1339 |
+
"num_tokens": 7901781.0,
|
| 1340 |
+
"step": 1330
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"entropy": 2.0273515924811365,
|
| 1344 |
+
"epoch": 2.3026004728132388,
|
| 1345 |
+
"grad_norm": 0.7098233103752136,
|
| 1346 |
+
"learning_rate": 0.00014644,
|
| 1347 |
+
"loss": 2.1501066207885744,
|
| 1348 |
+
"mean_token_accuracy": 0.6240016058087349,
|
| 1349 |
+
"num_tokens": 7962103.0,
|
| 1350 |
+
"step": 1340
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"entropy": 1.9079027369618415,
|
| 1354 |
+
"epoch": 2.3197936814958093,
|
| 1355 |
+
"grad_norm": 0.6738902926445007,
|
| 1356 |
+
"learning_rate": 0.00014604,
|
| 1357 |
+
"loss": 1.9681257247924804,
|
| 1358 |
+
"mean_token_accuracy": 0.6416124865412712,
|
| 1359 |
+
"num_tokens": 8021532.0,
|
| 1360 |
+
"step": 1350
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"entropy": 1.9230551555752755,
|
| 1364 |
+
"epoch": 2.3369868901783795,
|
| 1365 |
+
"grad_norm": 0.7348875999450684,
|
| 1366 |
+
"learning_rate": 0.00014564,
|
| 1367 |
+
"loss": 1.995201301574707,
|
| 1368 |
+
"mean_token_accuracy": 0.6393462974578142,
|
| 1369 |
+
"num_tokens": 8083084.0,
|
| 1370 |
+
"step": 1360
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"entropy": 1.9632413163781166,
|
| 1374 |
+
"epoch": 2.35418009886095,
|
| 1375 |
+
"grad_norm": 0.7093244194984436,
|
| 1376 |
+
"learning_rate": 0.00014523999999999998,
|
| 1377 |
+
"loss": 2.0105892181396485,
|
| 1378 |
+
"mean_token_accuracy": 0.6326792053878307,
|
| 1379 |
+
"num_tokens": 8144387.0,
|
| 1380 |
+
"step": 1370
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"entropy": 1.9028392255306243,
|
| 1384 |
+
"epoch": 2.37137330754352,
|
| 1385 |
+
"grad_norm": 0.7751646041870117,
|
| 1386 |
+
"learning_rate": 0.00014484,
|
| 1387 |
+
"loss": 1.9892047882080077,
|
| 1388 |
+
"mean_token_accuracy": 0.6404657427221536,
|
| 1389 |
+
"num_tokens": 8203720.0,
|
| 1390 |
+
"step": 1380
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"entropy": 1.860563676059246,
|
| 1394 |
+
"epoch": 2.3885665162260907,
|
| 1395 |
+
"grad_norm": 0.7243943214416504,
|
| 1396 |
+
"learning_rate": 0.00014444,
|
| 1397 |
+
"loss": 1.9201997756958007,
|
| 1398 |
+
"mean_token_accuracy": 0.6510312400758267,
|
| 1399 |
+
"num_tokens": 8263059.0,
|
| 1400 |
+
"step": 1390
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"entropy": 1.8883199632167815,
|
| 1404 |
+
"epoch": 2.405759724908661,
|
| 1405 |
+
"grad_norm": 0.6106081604957581,
|
| 1406 |
+
"learning_rate": 0.00014404,
|
| 1407 |
+
"loss": 1.9687911987304687,
|
| 1408 |
+
"mean_token_accuracy": 0.6493277192115784,
|
| 1409 |
+
"num_tokens": 8323826.0,
|
| 1410 |
+
"step": 1400
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"entropy": 1.9286921486258506,
|
| 1414 |
+
"epoch": 2.4229529335912314,
|
| 1415 |
+
"grad_norm": 0.697307825088501,
|
| 1416 |
+
"learning_rate": 0.00014364,
|
| 1417 |
+
"loss": 2.030810546875,
|
| 1418 |
+
"mean_token_accuracy": 0.6362422123551369,
|
| 1419 |
+
"num_tokens": 8383325.0,
|
| 1420 |
+
"step": 1410
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"entropy": 1.9122009217739104,
|
| 1424 |
+
"epoch": 2.440146142273802,
|
| 1425 |
+
"grad_norm": 0.7119978070259094,
|
| 1426 |
+
"learning_rate": 0.00014324,
|
| 1427 |
+
"loss": 1.9788457870483398,
|
| 1428 |
+
"mean_token_accuracy": 0.6400811962783337,
|
| 1429 |
+
"num_tokens": 8442393.0,
|
| 1430 |
+
"step": 1420
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"entropy": 1.9088031873106956,
|
| 1434 |
+
"epoch": 2.457339350956372,
|
| 1435 |
+
"grad_norm": 0.6792617440223694,
|
| 1436 |
+
"learning_rate": 0.00014284,
|
| 1437 |
+
"loss": 1.995138931274414,
|
| 1438 |
+
"mean_token_accuracy": 0.63965779915452,
|
| 1439 |
+
"num_tokens": 8501631.0,
|
| 1440 |
+
"step": 1430
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"entropy": 1.8871790513396263,
|
| 1444 |
+
"epoch": 2.4745325596389427,
|
| 1445 |
+
"grad_norm": 0.7191487550735474,
|
| 1446 |
+
"learning_rate": 0.00014244000000000003,
|
| 1447 |
+
"loss": 1.9728309631347656,
|
| 1448 |
+
"mean_token_accuracy": 0.642948642373085,
|
| 1449 |
+
"num_tokens": 8561457.0,
|
| 1450 |
+
"step": 1440
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"entropy": 1.8643269062042236,
|
| 1454 |
+
"epoch": 2.491725768321513,
|
| 1455 |
+
"grad_norm": 0.636345386505127,
|
| 1456 |
+
"learning_rate": 0.00014204000000000002,
|
| 1457 |
+
"loss": 1.9090641021728516,
|
| 1458 |
+
"mean_token_accuracy": 0.6537593178451061,
|
| 1459 |
+
"num_tokens": 8618281.0,
|
| 1460 |
+
"step": 1450
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"entropy": 1.90698651522398,
|
| 1464 |
+
"epoch": 2.5089189770040834,
|
| 1465 |
+
"grad_norm": 0.7444325685501099,
|
| 1466 |
+
"learning_rate": 0.00014164,
|
| 1467 |
+
"loss": 1.9631458282470704,
|
| 1468 |
+
"mean_token_accuracy": 0.6428062118589878,
|
| 1469 |
+
"num_tokens": 8675547.0,
|
| 1470 |
+
"step": 1460
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"entropy": 1.942822016775608,
|
| 1474 |
+
"epoch": 2.526112185686654,
|
| 1475 |
+
"grad_norm": 0.6707946062088013,
|
| 1476 |
+
"learning_rate": 0.00014124000000000002,
|
| 1477 |
+
"loss": 2.0348419189453124,
|
| 1478 |
+
"mean_token_accuracy": 0.6381070952862501,
|
| 1479 |
+
"num_tokens": 8735546.0,
|
| 1480 |
+
"step": 1470
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"entropy": 1.979990416765213,
|
| 1484 |
+
"epoch": 2.543305394369224,
|
| 1485 |
+
"grad_norm": 0.6958721280097961,
|
| 1486 |
+
"learning_rate": 0.00014084000000000001,
|
| 1487 |
+
"loss": 2.072053146362305,
|
| 1488 |
+
"mean_token_accuracy": 0.6283687971532345,
|
| 1489 |
+
"num_tokens": 8796404.0,
|
| 1490 |
+
"step": 1480
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"entropy": 1.9207274168729782,
|
| 1494 |
+
"epoch": 2.5604986030517947,
|
| 1495 |
+
"grad_norm": 0.6575210690498352,
|
| 1496 |
+
"learning_rate": 0.00014044,
|
| 1497 |
+
"loss": 1.9427066802978517,
|
| 1498 |
+
"mean_token_accuracy": 0.642588010430336,
|
| 1499 |
+
"num_tokens": 8853405.0,
|
| 1500 |
+
"step": 1490
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"entropy": 1.9980120360851288,
|
| 1504 |
+
"epoch": 2.577691811734365,
|
| 1505 |
+
"grad_norm": 0.7412211298942566,
|
| 1506 |
+
"learning_rate": 0.00014004000000000002,
|
| 1507 |
+
"loss": 2.1047718048095705,
|
| 1508 |
+
"mean_token_accuracy": 0.6264939974993468,
|
| 1509 |
+
"num_tokens": 8909416.0,
|
| 1510 |
+
"step": 1500
|
| 1511 |
}
|
| 1512 |
],
|
| 1513 |
"logging_steps": 10,
|
|
|
|
| 1527 |
"attributes": {}
|
| 1528 |
}
|
| 1529 |
},
|
| 1530 |
+
"total_flos": 7.314786665417933e+16,
|
| 1531 |
"train_batch_size": 2,
|
| 1532 |
"trial_name": null,
|
| 1533 |
"trial_params": null
|