Training in progress, step 1459, 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 2384234968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9831bb5e1e35eb5ed4ecb1b927fa6851453cf5a06fc1cc4390a9a213b31e41bc
|
| 3 |
size 2384234968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4768662910
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:643c1fb2bb7ea8916b25d0d480037eb4d301934ce55538f041d5e3fe49515bbd
|
| 3 |
size 4768662910
|
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 sha256:66e08749a49f64992fd7ac7288e0b5870a058f2e4c931055f9ea11441a8f2414
|
| 3 |
size 1064
|
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": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -908,6 +908,411 @@
|
|
| 908 |
"mean_token_accuracy": 0.974119370430708,
|
| 909 |
"num_tokens": 4096000.0,
|
| 910 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 911 |
}
|
| 912 |
],
|
| 913 |
"logging_steps": 10,
|
|
@@ -922,12 +1327,12 @@
|
|
| 922 |
"should_evaluate": false,
|
| 923 |
"should_log": false,
|
| 924 |
"should_save": true,
|
| 925 |
-
"should_training_stop":
|
| 926 |
},
|
| 927 |
"attributes": {}
|
| 928 |
}
|
| 929 |
},
|
| 930 |
-
"total_flos": 1.
|
| 931 |
"train_batch_size": 1,
|
| 932 |
"trial_name": null,
|
| 933 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9994006336158918,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 1459,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 908 |
"mean_token_accuracy": 0.974119370430708,
|
| 909 |
"num_tokens": 4096000.0,
|
| 910 |
"step": 1000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.6918400547992123,
|
| 914 |
+
"grad_norm": 0.7098048329353333,
|
| 915 |
+
"learning_rate": 1.7136329017517136e-05,
|
| 916 |
+
"loss": 0.1468,
|
| 917 |
+
"mean_token_accuracy": 0.9731898210942745,
|
| 918 |
+
"num_tokens": 4136960.0,
|
| 919 |
+
"step": 1010
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.6986899563318777,
|
| 923 |
+
"grad_norm": 0.784039318561554,
|
| 924 |
+
"learning_rate": 1.6755521706016754e-05,
|
| 925 |
+
"loss": 0.1281,
|
| 926 |
+
"mean_token_accuracy": 0.9749999955296517,
|
| 927 |
+
"num_tokens": 4177920.0,
|
| 928 |
+
"step": 1020
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.7055398578645432,
|
| 932 |
+
"grad_norm": 0.7651719450950623,
|
| 933 |
+
"learning_rate": 1.6374714394516375e-05,
|
| 934 |
+
"loss": 0.1362,
|
| 935 |
+
"mean_token_accuracy": 0.9742906041443348,
|
| 936 |
+
"num_tokens": 4218880.0,
|
| 937 |
+
"step": 1030
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.7123897593972086,
|
| 941 |
+
"grad_norm": 0.6100867390632629,
|
| 942 |
+
"learning_rate": 1.5993907083015994e-05,
|
| 943 |
+
"loss": 0.132,
|
| 944 |
+
"mean_token_accuracy": 0.9753180012106896,
|
| 945 |
+
"num_tokens": 4259840.0,
|
| 946 |
+
"step": 1040
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.7192396609298741,
|
| 950 |
+
"grad_norm": 0.789665162563324,
|
| 951 |
+
"learning_rate": 1.561309977151561e-05,
|
| 952 |
+
"loss": 0.1362,
|
| 953 |
+
"mean_token_accuracy": 0.974975535273552,
|
| 954 |
+
"num_tokens": 4300800.0,
|
| 955 |
+
"step": 1050
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.7260895624625396,
|
| 959 |
+
"grad_norm": 0.7343530058860779,
|
| 960 |
+
"learning_rate": 1.5232292460015233e-05,
|
| 961 |
+
"loss": 0.1338,
|
| 962 |
+
"mean_token_accuracy": 0.9751712307333946,
|
| 963 |
+
"num_tokens": 4341760.0,
|
| 964 |
+
"step": 1060
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.732939463995205,
|
| 968 |
+
"grad_norm": 0.6612673997879028,
|
| 969 |
+
"learning_rate": 1.4851485148514851e-05,
|
| 970 |
+
"loss": 0.1346,
|
| 971 |
+
"mean_token_accuracy": 0.9744862951338291,
|
| 972 |
+
"num_tokens": 4382720.0,
|
| 973 |
+
"step": 1070
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.7397893655278706,
|
| 977 |
+
"grad_norm": 0.6594858765602112,
|
| 978 |
+
"learning_rate": 1.4470677837014471e-05,
|
| 979 |
+
"loss": 0.1239,
|
| 980 |
+
"mean_token_accuracy": 0.9765900149941444,
|
| 981 |
+
"num_tokens": 4423680.0,
|
| 982 |
+
"step": 1080
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.746639267060536,
|
| 986 |
+
"grad_norm": 0.8898121118545532,
|
| 987 |
+
"learning_rate": 1.408987052551409e-05,
|
| 988 |
+
"loss": 0.1309,
|
| 989 |
+
"mean_token_accuracy": 0.9749021507799626,
|
| 990 |
+
"num_tokens": 4464640.0,
|
| 991 |
+
"step": 1090
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.7534891685932015,
|
| 995 |
+
"grad_norm": 1.0296205282211304,
|
| 996 |
+
"learning_rate": 1.3709063214013709e-05,
|
| 997 |
+
"loss": 0.1333,
|
| 998 |
+
"mean_token_accuracy": 0.9747553780674935,
|
| 999 |
+
"num_tokens": 4505600.0,
|
| 1000 |
+
"step": 1100
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.760339070125867,
|
| 1004 |
+
"grad_norm": 0.7691386938095093,
|
| 1005 |
+
"learning_rate": 1.3328255902513328e-05,
|
| 1006 |
+
"loss": 0.1371,
|
| 1007 |
+
"mean_token_accuracy": 0.9743639886379242,
|
| 1008 |
+
"num_tokens": 4546560.0,
|
| 1009 |
+
"step": 1110
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.7671889716585324,
|
| 1013 |
+
"grad_norm": 0.6772127151489258,
|
| 1014 |
+
"learning_rate": 1.2947448591012948e-05,
|
| 1015 |
+
"loss": 0.1272,
|
| 1016 |
+
"mean_token_accuracy": 0.9763209350407124,
|
| 1017 |
+
"num_tokens": 4587520.0,
|
| 1018 |
+
"step": 1120
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.7740388731911979,
|
| 1022 |
+
"grad_norm": 0.8715652227401733,
|
| 1023 |
+
"learning_rate": 1.2566641279512566e-05,
|
| 1024 |
+
"loss": 0.1355,
|
| 1025 |
+
"mean_token_accuracy": 0.9732142828404904,
|
| 1026 |
+
"num_tokens": 4628480.0,
|
| 1027 |
+
"step": 1130
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.7808887747238633,
|
| 1031 |
+
"grad_norm": 0.723171055316925,
|
| 1032 |
+
"learning_rate": 1.2185833968012186e-05,
|
| 1033 |
+
"loss": 0.1303,
|
| 1034 |
+
"mean_token_accuracy": 0.9756360031664372,
|
| 1035 |
+
"num_tokens": 4669440.0,
|
| 1036 |
+
"step": 1140
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.7877386762565288,
|
| 1040 |
+
"grad_norm": 0.7655256986618042,
|
| 1041 |
+
"learning_rate": 1.1805026656511806e-05,
|
| 1042 |
+
"loss": 0.1344,
|
| 1043 |
+
"mean_token_accuracy": 0.9737279817461968,
|
| 1044 |
+
"num_tokens": 4710400.0,
|
| 1045 |
+
"step": 1150
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.7945885777891942,
|
| 1049 |
+
"grad_norm": 0.7253991365432739,
|
| 1050 |
+
"learning_rate": 1.1424219345011426e-05,
|
| 1051 |
+
"loss": 0.1303,
|
| 1052 |
+
"mean_token_accuracy": 0.9757093906402587,
|
| 1053 |
+
"num_tokens": 4751360.0,
|
| 1054 |
+
"step": 1160
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.8014384793218597,
|
| 1058 |
+
"grad_norm": 0.8294143080711365,
|
| 1059 |
+
"learning_rate": 1.1043412033511044e-05,
|
| 1060 |
+
"loss": 0.1349,
|
| 1061 |
+
"mean_token_accuracy": 0.9750489175319672,
|
| 1062 |
+
"num_tokens": 4792320.0,
|
| 1063 |
+
"step": 1170
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.8082883808545253,
|
| 1067 |
+
"grad_norm": 0.7206155061721802,
|
| 1068 |
+
"learning_rate": 1.0662604722010663e-05,
|
| 1069 |
+
"loss": 0.1298,
|
| 1070 |
+
"mean_token_accuracy": 0.975220151245594,
|
| 1071 |
+
"num_tokens": 4833280.0,
|
| 1072 |
+
"step": 1180
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.8151382823871907,
|
| 1076 |
+
"grad_norm": 0.6955848336219788,
|
| 1077 |
+
"learning_rate": 1.0281797410510283e-05,
|
| 1078 |
+
"loss": 0.1245,
|
| 1079 |
+
"mean_token_accuracy": 0.9763453997671604,
|
| 1080 |
+
"num_tokens": 4874240.0,
|
| 1081 |
+
"step": 1190
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.8219881839198562,
|
| 1085 |
+
"grad_norm": 0.9156601428985596,
|
| 1086 |
+
"learning_rate": 9.900990099009901e-06,
|
| 1087 |
+
"loss": 0.1289,
|
| 1088 |
+
"mean_token_accuracy": 0.9753913819789887,
|
| 1089 |
+
"num_tokens": 4915200.0,
|
| 1090 |
+
"step": 1200
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.8288380854525216,
|
| 1094 |
+
"grad_norm": 0.7370653748512268,
|
| 1095 |
+
"learning_rate": 9.520182787509521e-06,
|
| 1096 |
+
"loss": 0.1268,
|
| 1097 |
+
"mean_token_accuracy": 0.9757827781140804,
|
| 1098 |
+
"num_tokens": 4956160.0,
|
| 1099 |
+
"step": 1210
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.8356879869851871,
|
| 1103 |
+
"grad_norm": 0.8186970353126526,
|
| 1104 |
+
"learning_rate": 9.13937547600914e-06,
|
| 1105 |
+
"loss": 0.139,
|
| 1106 |
+
"mean_token_accuracy": 0.9738747522234916,
|
| 1107 |
+
"num_tokens": 4997120.0,
|
| 1108 |
+
"step": 1220
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.8425378885178526,
|
| 1112 |
+
"grad_norm": 0.7266510128974915,
|
| 1113 |
+
"learning_rate": 8.758568164508759e-06,
|
| 1114 |
+
"loss": 0.1344,
|
| 1115 |
+
"mean_token_accuracy": 0.9744373761117459,
|
| 1116 |
+
"num_tokens": 5038080.0,
|
| 1117 |
+
"step": 1230
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 0.849387790050518,
|
| 1121 |
+
"grad_norm": 0.7429907321929932,
|
| 1122 |
+
"learning_rate": 8.377760853008377e-06,
|
| 1123 |
+
"loss": 0.136,
|
| 1124 |
+
"mean_token_accuracy": 0.9745841458439827,
|
| 1125 |
+
"num_tokens": 5079040.0,
|
| 1126 |
+
"step": 1240
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.8562376915831835,
|
| 1130 |
+
"grad_norm": 0.6797091364860535,
|
| 1131 |
+
"learning_rate": 7.996953541507997e-06,
|
| 1132 |
+
"loss": 0.1364,
|
| 1133 |
+
"mean_token_accuracy": 0.9743395261466503,
|
| 1134 |
+
"num_tokens": 5120000.0,
|
| 1135 |
+
"step": 1250
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 0.8630875931158489,
|
| 1139 |
+
"grad_norm": 0.6236211061477661,
|
| 1140 |
+
"learning_rate": 7.6161462300076165e-06,
|
| 1141 |
+
"loss": 0.1247,
|
| 1142 |
+
"mean_token_accuracy": 0.9762230902910233,
|
| 1143 |
+
"num_tokens": 5160960.0,
|
| 1144 |
+
"step": 1260
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.8699374946485144,
|
| 1148 |
+
"grad_norm": 1.0793285369873047,
|
| 1149 |
+
"learning_rate": 7.2353389185072354e-06,
|
| 1150 |
+
"loss": 0.1384,
|
| 1151 |
+
"mean_token_accuracy": 0.9733121328055858,
|
| 1152 |
+
"num_tokens": 5201920.0,
|
| 1153 |
+
"step": 1270
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.8767873961811798,
|
| 1157 |
+
"grad_norm": 0.7861872911453247,
|
| 1158 |
+
"learning_rate": 6.854531607006854e-06,
|
| 1159 |
+
"loss": 0.1303,
|
| 1160 |
+
"mean_token_accuracy": 0.9757093906402587,
|
| 1161 |
+
"num_tokens": 5242880.0,
|
| 1162 |
+
"step": 1280
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.8836372977138454,
|
| 1166 |
+
"grad_norm": 0.6387534141540527,
|
| 1167 |
+
"learning_rate": 6.473724295506474e-06,
|
| 1168 |
+
"loss": 0.1276,
|
| 1169 |
+
"mean_token_accuracy": 0.9762964725494385,
|
| 1170 |
+
"num_tokens": 5283840.0,
|
| 1171 |
+
"step": 1290
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.8904871992465109,
|
| 1175 |
+
"grad_norm": 0.8344358801841736,
|
| 1176 |
+
"learning_rate": 6.092916984006093e-06,
|
| 1177 |
+
"loss": 0.1265,
|
| 1178 |
+
"mean_token_accuracy": 0.9753424629569054,
|
| 1179 |
+
"num_tokens": 5324800.0,
|
| 1180 |
+
"step": 1300
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.8973371007791763,
|
| 1184 |
+
"grad_norm": 0.847582995891571,
|
| 1185 |
+
"learning_rate": 5.712109672505713e-06,
|
| 1186 |
+
"loss": 0.1279,
|
| 1187 |
+
"mean_token_accuracy": 0.9758561603724957,
|
| 1188 |
+
"num_tokens": 5365760.0,
|
| 1189 |
+
"step": 1310
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.9041870023118418,
|
| 1193 |
+
"grad_norm": 0.9168363809585571,
|
| 1194 |
+
"learning_rate": 5.331302361005332e-06,
|
| 1195 |
+
"loss": 0.1372,
|
| 1196 |
+
"mean_token_accuracy": 0.9740215204656124,
|
| 1197 |
+
"num_tokens": 5406720.0,
|
| 1198 |
+
"step": 1320
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 0.9110369038445072,
|
| 1202 |
+
"grad_norm": 0.8992748856544495,
|
| 1203 |
+
"learning_rate": 4.950495049504951e-06,
|
| 1204 |
+
"loss": 0.1267,
|
| 1205 |
+
"mean_token_accuracy": 0.9755381584167481,
|
| 1206 |
+
"num_tokens": 5447680.0,
|
| 1207 |
+
"step": 1330
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.9178868053771727,
|
| 1211 |
+
"grad_norm": 0.8741844296455383,
|
| 1212 |
+
"learning_rate": 4.56968773800457e-06,
|
| 1213 |
+
"loss": 0.1305,
|
| 1214 |
+
"mean_token_accuracy": 0.974828764051199,
|
| 1215 |
+
"num_tokens": 5488640.0,
|
| 1216 |
+
"step": 1340
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.9247367069098382,
|
| 1220 |
+
"grad_norm": 0.8191506862640381,
|
| 1221 |
+
"learning_rate": 4.1888804265041885e-06,
|
| 1222 |
+
"loss": 0.1298,
|
| 1223 |
+
"mean_token_accuracy": 0.9747309193015099,
|
| 1224 |
+
"num_tokens": 5529600.0,
|
| 1225 |
+
"step": 1350
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.9315866084425036,
|
| 1229 |
+
"grad_norm": 0.7575434446334839,
|
| 1230 |
+
"learning_rate": 3.8080731150038083e-06,
|
| 1231 |
+
"loss": 0.1357,
|
| 1232 |
+
"mean_token_accuracy": 0.9738013677299022,
|
| 1233 |
+
"num_tokens": 5570560.0,
|
| 1234 |
+
"step": 1360
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9384365099751691,
|
| 1238 |
+
"grad_norm": 0.8960770964622498,
|
| 1239 |
+
"learning_rate": 3.427265803503427e-06,
|
| 1240 |
+
"loss": 0.1213,
|
| 1241 |
+
"mean_token_accuracy": 0.9772749491035938,
|
| 1242 |
+
"num_tokens": 5611520.0,
|
| 1243 |
+
"step": 1370
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.9452864115078345,
|
| 1247 |
+
"grad_norm": 0.6886873841285706,
|
| 1248 |
+
"learning_rate": 3.0464584920030465e-06,
|
| 1249 |
+
"loss": 0.1228,
|
| 1250 |
+
"mean_token_accuracy": 0.9769324824213982,
|
| 1251 |
+
"num_tokens": 5652480.0,
|
| 1252 |
+
"step": 1380
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.9521363130405001,
|
| 1256 |
+
"grad_norm": 0.606661319732666,
|
| 1257 |
+
"learning_rate": 2.665651180502666e-06,
|
| 1258 |
+
"loss": 0.1297,
|
| 1259 |
+
"mean_token_accuracy": 0.9750244595110417,
|
| 1260 |
+
"num_tokens": 5693440.0,
|
| 1261 |
+
"step": 1390
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.9589862145731655,
|
| 1265 |
+
"grad_norm": 0.7276999950408936,
|
| 1266 |
+
"learning_rate": 2.284843869002285e-06,
|
| 1267 |
+
"loss": 0.1398,
|
| 1268 |
+
"mean_token_accuracy": 0.9740215227007866,
|
| 1269 |
+
"num_tokens": 5734400.0,
|
| 1270 |
+
"step": 1400
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.965836116105831,
|
| 1274 |
+
"grad_norm": 0.7728492021560669,
|
| 1275 |
+
"learning_rate": 1.9040365575019041e-06,
|
| 1276 |
+
"loss": 0.1288,
|
| 1277 |
+
"mean_token_accuracy": 0.9757827736437321,
|
| 1278 |
+
"num_tokens": 5775360.0,
|
| 1279 |
+
"step": 1410
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.9726860176384965,
|
| 1283 |
+
"grad_norm": 0.6705936193466187,
|
| 1284 |
+
"learning_rate": 1.5232292460015233e-06,
|
| 1285 |
+
"loss": 0.1246,
|
| 1286 |
+
"mean_token_accuracy": 0.9765166334807873,
|
| 1287 |
+
"num_tokens": 5816320.0,
|
| 1288 |
+
"step": 1420
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 0.9795359191711619,
|
| 1292 |
+
"grad_norm": 1.092812418937683,
|
| 1293 |
+
"learning_rate": 1.1424219345011426e-06,
|
| 1294 |
+
"loss": 0.1269,
|
| 1295 |
+
"mean_token_accuracy": 0.9758806228637695,
|
| 1296 |
+
"num_tokens": 5857280.0,
|
| 1297 |
+
"step": 1430
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.9863858207038274,
|
| 1301 |
+
"grad_norm": 0.7121983170509338,
|
| 1302 |
+
"learning_rate": 7.616146230007616e-07,
|
| 1303 |
+
"loss": 0.1245,
|
| 1304 |
+
"mean_token_accuracy": 0.9758806228637695,
|
| 1305 |
+
"num_tokens": 5898240.0,
|
| 1306 |
+
"step": 1440
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.9932357222364928,
|
| 1310 |
+
"grad_norm": 0.6971803307533264,
|
| 1311 |
+
"learning_rate": 3.808073115003808e-07,
|
| 1312 |
+
"loss": 0.1298,
|
| 1313 |
+
"mean_token_accuracy": 0.9753179982304573,
|
| 1314 |
+
"num_tokens": 5939200.0,
|
| 1315 |
+
"step": 1450
|
| 1316 |
}
|
| 1317 |
],
|
| 1318 |
"logging_steps": 10,
|
|
|
|
| 1327 |
"should_evaluate": false,
|
| 1328 |
"should_log": false,
|
| 1329 |
"should_save": true,
|
| 1330 |
+
"should_training_stop": true
|
| 1331 |
},
|
| 1332 |
"attributes": {}
|
| 1333 |
}
|
| 1334 |
},
|
| 1335 |
+
"total_flos": 1.5793570241839104e+16,
|
| 1336 |
"train_batch_size": 1,
|
| 1337 |
"trial_name": null,
|
| 1338 |
"trial_params": null
|