Training in progress, step 1600, 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 2433024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f461d6c9104ce6907b4e7c31e27d59f5ac89572d6389be328116c94be46dfc90
|
| 3 |
size 2433024
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2498406
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fceeac08bcbf067a45f25c4cabdca0559cd7fb797d80d8ee1f9a373872298b8
|
| 3 |
size 2498406
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ced0ac0d077b41bd2987add3782b7ce1140142ac3cddaf433babda96674c50fb
|
| 3 |
size 14244
|
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 sha256:9ed6aad8025a80b776f2d50234fd05b8c1e2e758d3d427458fe15ed9bc7f733a
|
| 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": 0.
|
| 5 |
"eval_steps": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -903,6 +903,302 @@
|
|
| 903 |
"eval_samples_per_second": 40.706,
|
| 904 |
"eval_steps_per_second": 10.19,
|
| 905 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 906 |
}
|
| 907 |
],
|
| 908 |
"logging_steps": 10,
|
|
@@ -922,7 +1218,7 @@
|
|
| 922 |
"attributes": {}
|
| 923 |
}
|
| 924 |
},
|
| 925 |
-
"total_flos":
|
| 926 |
"train_batch_size": 4,
|
| 927 |
"trial_name": null,
|
| 928 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.47351287363125183,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 1600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 903 |
"eval_samples_per_second": 40.706,
|
| 904 |
"eval_steps_per_second": 10.19,
|
| 905 |
"step": 1200
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.3580941106836342,
|
| 909 |
+
"grad_norm": 0.57421875,
|
| 910 |
+
"learning_rate": 0.0001135169494631497,
|
| 911 |
+
"loss": 10.541,
|
| 912 |
+
"step": 1210
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.36105356614382955,
|
| 916 |
+
"grad_norm": 0.58984375,
|
| 917 |
+
"learning_rate": 0.00011220516908034601,
|
| 918 |
+
"loss": 10.5805,
|
| 919 |
+
"step": 1220
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.3640130216040249,
|
| 923 |
+
"grad_norm": 0.52734375,
|
| 924 |
+
"learning_rate": 0.00011089125314635726,
|
| 925 |
+
"loss": 10.6207,
|
| 926 |
+
"step": 1230
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.3669724770642202,
|
| 930 |
+
"grad_norm": 0.734375,
|
| 931 |
+
"learning_rate": 0.00010957543155842702,
|
| 932 |
+
"loss": 10.6731,
|
| 933 |
+
"step": 1240
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.36993193252441553,
|
| 937 |
+
"grad_norm": 0.765625,
|
| 938 |
+
"learning_rate": 0.00010825793454723325,
|
| 939 |
+
"loss": 10.5913,
|
| 940 |
+
"step": 1250
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.37289138798461086,
|
| 944 |
+
"grad_norm": 0.490234375,
|
| 945 |
+
"learning_rate": 0.00010693899263660441,
|
| 946 |
+
"loss": 10.5151,
|
| 947 |
+
"step": 1260
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.3758508434448062,
|
| 951 |
+
"grad_norm": 0.515625,
|
| 952 |
+
"learning_rate": 0.00010561883660318455,
|
| 953 |
+
"loss": 10.5782,
|
| 954 |
+
"step": 1270
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.37881029890500145,
|
| 958 |
+
"grad_norm": 1.1015625,
|
| 959 |
+
"learning_rate": 0.00010429769743605407,
|
| 960 |
+
"loss": 10.5898,
|
| 961 |
+
"step": 1280
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.3817697543651968,
|
| 965 |
+
"grad_norm": 0.60546875,
|
| 966 |
+
"learning_rate": 0.00010297580629631325,
|
| 967 |
+
"loss": 10.5216,
|
| 968 |
+
"step": 1290
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.3847292098253921,
|
| 972 |
+
"grad_norm": 1.4921875,
|
| 973 |
+
"learning_rate": 0.00010165339447663587,
|
| 974 |
+
"loss": 10.4868,
|
| 975 |
+
"step": 1300
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.38768866528558743,
|
| 979 |
+
"grad_norm": 0.44140625,
|
| 980 |
+
"learning_rate": 0.00010033069336079952,
|
| 981 |
+
"loss": 10.6363,
|
| 982 |
+
"step": 1310
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.39064812074578276,
|
| 986 |
+
"grad_norm": 0.515625,
|
| 987 |
+
"learning_rate": 9.900793438320037e-05,
|
| 988 |
+
"loss": 10.55,
|
| 989 |
+
"step": 1320
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.3936075762059781,
|
| 993 |
+
"grad_norm": 0.703125,
|
| 994 |
+
"learning_rate": 9.768534898835862e-05,
|
| 995 |
+
"loss": 10.6171,
|
| 996 |
+
"step": 1330
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.3965670316661734,
|
| 1000 |
+
"grad_norm": 0.69140625,
|
| 1001 |
+
"learning_rate": 9.636316859042259e-05,
|
| 1002 |
+
"loss": 10.6343,
|
| 1003 |
+
"step": 1340
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.39952648712636873,
|
| 1007 |
+
"grad_norm": 1.171875,
|
| 1008 |
+
"learning_rate": 9.504162453267777e-05,
|
| 1009 |
+
"loss": 10.6261,
|
| 1010 |
+
"step": 1350
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.40248594258656406,
|
| 1014 |
+
"grad_norm": 0.49609375,
|
| 1015 |
+
"learning_rate": 9.372094804706867e-05,
|
| 1016 |
+
"loss": 10.566,
|
| 1017 |
+
"step": 1360
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.4054453980467594,
|
| 1021 |
+
"grad_norm": 0.54296875,
|
| 1022 |
+
"learning_rate": 9.24013702137397e-05,
|
| 1023 |
+
"loss": 10.5186,
|
| 1024 |
+
"step": 1370
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.4084048535069547,
|
| 1028 |
+
"grad_norm": 0.5546875,
|
| 1029 |
+
"learning_rate": 9.108312192060298e-05,
|
| 1030 |
+
"loss": 10.6343,
|
| 1031 |
+
"step": 1380
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.41136430896715004,
|
| 1035 |
+
"grad_norm": 0.83984375,
|
| 1036 |
+
"learning_rate": 8.97664338229395e-05,
|
| 1037 |
+
"loss": 10.6551,
|
| 1038 |
+
"step": 1390
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.41432376442734536,
|
| 1042 |
+
"grad_norm": 2.859375,
|
| 1043 |
+
"learning_rate": 8.845153630304139e-05,
|
| 1044 |
+
"loss": 10.6436,
|
| 1045 |
+
"step": 1400
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.41432376442734536,
|
| 1049 |
+
"eval_loss": 10.585193634033203,
|
| 1050 |
+
"eval_runtime": 37.153,
|
| 1051 |
+
"eval_samples_per_second": 40.427,
|
| 1052 |
+
"eval_steps_per_second": 10.12,
|
| 1053 |
+
"step": 1400
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.4172832198875407,
|
| 1057 |
+
"grad_norm": 0.53125,
|
| 1058 |
+
"learning_rate": 8.713865942990141e-05,
|
| 1059 |
+
"loss": 10.5189,
|
| 1060 |
+
"step": 1410
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.420242675347736,
|
| 1064 |
+
"grad_norm": 0.53515625,
|
| 1065 |
+
"learning_rate": 8.582803291895758e-05,
|
| 1066 |
+
"loss": 10.4783,
|
| 1067 |
+
"step": 1420
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.42320213080793134,
|
| 1071 |
+
"grad_norm": 0.5390625,
|
| 1072 |
+
"learning_rate": 8.451988609189987e-05,
|
| 1073 |
+
"loss": 10.6285,
|
| 1074 |
+
"step": 1430
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.42616158626812667,
|
| 1078 |
+
"grad_norm": 0.63671875,
|
| 1079 |
+
"learning_rate": 8.321444783654524e-05,
|
| 1080 |
+
"loss": 10.7481,
|
| 1081 |
+
"step": 1440
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.429121041728322,
|
| 1085 |
+
"grad_norm": 1.0703125,
|
| 1086 |
+
"learning_rate": 8.191194656678904e-05,
|
| 1087 |
+
"loss": 10.6971,
|
| 1088 |
+
"step": 1450
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.4320804971885173,
|
| 1092 |
+
"grad_norm": 0.5078125,
|
| 1093 |
+
"learning_rate": 8.061261018263919e-05,
|
| 1094 |
+
"loss": 10.5323,
|
| 1095 |
+
"step": 1460
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.43503995264871265,
|
| 1099 |
+
"grad_norm": 0.51171875,
|
| 1100 |
+
"learning_rate": 7.931666603034033e-05,
|
| 1101 |
+
"loss": 10.4634,
|
| 1102 |
+
"step": 1470
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.437999408108908,
|
| 1106 |
+
"grad_norm": 0.6171875,
|
| 1107 |
+
"learning_rate": 7.80243408625947e-05,
|
| 1108 |
+
"loss": 10.5384,
|
| 1109 |
+
"step": 1480
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.4409588635691033,
|
| 1113 |
+
"grad_norm": 0.76953125,
|
| 1114 |
+
"learning_rate": 7.673586079888698e-05,
|
| 1115 |
+
"loss": 10.699,
|
| 1116 |
+
"step": 1490
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.4439183190292986,
|
| 1120 |
+
"grad_norm": 1.5390625,
|
| 1121 |
+
"learning_rate": 7.54514512859201e-05,
|
| 1122 |
+
"loss": 10.5729,
|
| 1123 |
+
"step": 1500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.44687777448949395,
|
| 1127 |
+
"grad_norm": 0.455078125,
|
| 1128 |
+
"learning_rate": 7.417133705816837e-05,
|
| 1129 |
+
"loss": 10.5262,
|
| 1130 |
+
"step": 1510
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.4498372299496893,
|
| 1134 |
+
"grad_norm": 0.6640625,
|
| 1135 |
+
"learning_rate": 7.289574209855559e-05,
|
| 1136 |
+
"loss": 10.5102,
|
| 1137 |
+
"step": 1520
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.4527966854098846,
|
| 1141 |
+
"grad_norm": 0.5703125,
|
| 1142 |
+
"learning_rate": 7.16248895992645e-05,
|
| 1143 |
+
"loss": 10.6538,
|
| 1144 |
+
"step": 1530
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.45575614087007993,
|
| 1148 |
+
"grad_norm": 0.83203125,
|
| 1149 |
+
"learning_rate": 7.035900192268464e-05,
|
| 1150 |
+
"loss": 10.4972,
|
| 1151 |
+
"step": 1540
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.45871559633027525,
|
| 1155 |
+
"grad_norm": 0.90625,
|
| 1156 |
+
"learning_rate": 6.909830056250527e-05,
|
| 1157 |
+
"loss": 10.646,
|
| 1158 |
+
"step": 1550
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.4616750517904706,
|
| 1162 |
+
"grad_norm": 0.494140625,
|
| 1163 |
+
"learning_rate": 6.784300610496048e-05,
|
| 1164 |
+
"loss": 10.564,
|
| 1165 |
+
"step": 1560
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.46463450725066585,
|
| 1169 |
+
"grad_norm": 0.57421875,
|
| 1170 |
+
"learning_rate": 6.65933381902329e-05,
|
| 1171 |
+
"loss": 10.5419,
|
| 1172 |
+
"step": 1570
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.4675939627108612,
|
| 1176 |
+
"grad_norm": 0.5703125,
|
| 1177 |
+
"learning_rate": 6.534951547402322e-05,
|
| 1178 |
+
"loss": 10.6451,
|
| 1179 |
+
"step": 1580
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.4705534181710565,
|
| 1183 |
+
"grad_norm": 0.7578125,
|
| 1184 |
+
"learning_rate": 6.411175558929152e-05,
|
| 1185 |
+
"loss": 10.7074,
|
| 1186 |
+
"step": 1590
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.47351287363125183,
|
| 1190 |
+
"grad_norm": 0.98046875,
|
| 1191 |
+
"learning_rate": 6.28802751081779e-05,
|
| 1192 |
+
"loss": 10.5774,
|
| 1193 |
+
"step": 1600
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.47351287363125183,
|
| 1197 |
+
"eval_loss": 10.587952613830566,
|
| 1198 |
+
"eval_runtime": 36.8828,
|
| 1199 |
+
"eval_samples_per_second": 40.724,
|
| 1200 |
+
"eval_steps_per_second": 10.194,
|
| 1201 |
+
"step": 1600
|
| 1202 |
}
|
| 1203 |
],
|
| 1204 |
"logging_steps": 10,
|
|
|
|
| 1218 |
"attributes": {}
|
| 1219 |
}
|
| 1220 |
},
|
| 1221 |
+
"total_flos": 156755165184.0,
|
| 1222 |
"train_batch_size": 4,
|
| 1223 |
"trial_name": null,
|
| 1224 |
"trial_params": null
|