Training in progress, step 1500, 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 sha256:782e8ac1da50805a0148b309fba266f389439b051c131233056ebbdcad3f58ee
|
| 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 4768663315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c664d5bbe4243e2d8db79e79e6b2516a49619d23a025b2135048a5763a753ef7
|
| 3 |
size 4768663315
|
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 sha256:2534e434cd5abbb8f7668d3eab0549db0ef95d6a797a3efa86b712e8e32266a7
|
| 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 sha256:83e59f17c2c0681a7d8c091fe9bc022de98a5c7804170d371d6b77c623b084c5
|
| 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": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -908,6 +908,456 @@
|
|
| 908 |
"mean_token_accuracy": 0.935359588265419,
|
| 909 |
"num_tokens": 8186880.0,
|
| 910 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 911 |
}
|
| 912 |
],
|
| 913 |
"logging_steps": 10,
|
|
@@ -927,7 +1377,7 @@
|
|
| 927 |
"attributes": {}
|
| 928 |
}
|
| 929 |
},
|
| 930 |
-
"total_flos":
|
| 931 |
"train_batch_size": 2,
|
| 932 |
"trial_name": null,
|
| 933 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.9481190066388,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 908 |
"mean_token_accuracy": 0.935359588265419,
|
| 909 |
"num_tokens": 8186880.0,
|
| 910 |
"step": 1000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.985492992377674,
|
| 914 |
+
"grad_norm": 0.6394369602203369,
|
| 915 |
+
"learning_rate": 3.770014556040757e-06,
|
| 916 |
+
"loss": 0.0759,
|
| 917 |
+
"mean_token_accuracy": 0.9349559672176838,
|
| 918 |
+
"num_tokens": 8268800.0,
|
| 919 |
+
"step": 1010
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.0039341037619867,
|
| 923 |
+
"grad_norm": 0.7817333340644836,
|
| 924 |
+
"learning_rate": 3.6972343522561864e-06,
|
| 925 |
+
"loss": 0.0759,
|
| 926 |
+
"mean_token_accuracy": 0.935172860622406,
|
| 927 |
+
"num_tokens": 8345600.0,
|
| 928 |
+
"step": 1020
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.0236046225719204,
|
| 932 |
+
"grad_norm": 0.8923552632331848,
|
| 933 |
+
"learning_rate": 3.624454148471616e-06,
|
| 934 |
+
"loss": 0.0694,
|
| 935 |
+
"mean_token_accuracy": 0.937181992828846,
|
| 936 |
+
"num_tokens": 8427520.0,
|
| 937 |
+
"step": 1030
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 2.0432751413818537,
|
| 941 |
+
"grad_norm": 0.7769061326980591,
|
| 942 |
+
"learning_rate": 3.551673944687045e-06,
|
| 943 |
+
"loss": 0.0723,
|
| 944 |
+
"mean_token_accuracy": 0.9345278829336167,
|
| 945 |
+
"num_tokens": 8509440.0,
|
| 946 |
+
"step": 1040
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.0629456601917875,
|
| 950 |
+
"grad_norm": 0.6698974967002869,
|
| 951 |
+
"learning_rate": 3.4788937409024746e-06,
|
| 952 |
+
"loss": 0.0712,
|
| 953 |
+
"mean_token_accuracy": 0.9358243614435195,
|
| 954 |
+
"num_tokens": 8591360.0,
|
| 955 |
+
"step": 1050
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.0826161790017212,
|
| 959 |
+
"grad_norm": 0.8802694082260132,
|
| 960 |
+
"learning_rate": 3.406113537117904e-06,
|
| 961 |
+
"loss": 0.0687,
|
| 962 |
+
"mean_token_accuracy": 0.9373654581606388,
|
| 963 |
+
"num_tokens": 8673280.0,
|
| 964 |
+
"step": 1060
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.102286697811655,
|
| 968 |
+
"grad_norm": 1.0914084911346436,
|
| 969 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 970 |
+
"loss": 0.0727,
|
| 971 |
+
"mean_token_accuracy": 0.9355552814900875,
|
| 972 |
+
"num_tokens": 8755200.0,
|
| 973 |
+
"step": 1070
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 2.1219572166215883,
|
| 977 |
+
"grad_norm": 0.9575169086456299,
|
| 978 |
+
"learning_rate": 3.260553129548763e-06,
|
| 979 |
+
"loss": 0.0693,
|
| 980 |
+
"mean_token_accuracy": 0.9379770055413246,
|
| 981 |
+
"num_tokens": 8837120.0,
|
| 982 |
+
"step": 1080
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.141627735431522,
|
| 986 |
+
"grad_norm": 0.7972959876060486,
|
| 987 |
+
"learning_rate": 3.1877729257641924e-06,
|
| 988 |
+
"loss": 0.067,
|
| 989 |
+
"mean_token_accuracy": 0.9371819935739041,
|
| 990 |
+
"num_tokens": 8919040.0,
|
| 991 |
+
"step": 1090
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.161298254241456,
|
| 995 |
+
"grad_norm": 0.9708478450775146,
|
| 996 |
+
"learning_rate": 3.1149927219796215e-06,
|
| 997 |
+
"loss": 0.0728,
|
| 998 |
+
"mean_token_accuracy": 0.9354329705238342,
|
| 999 |
+
"num_tokens": 9000960.0,
|
| 1000 |
+
"step": 1100
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.180968773051389,
|
| 1004 |
+
"grad_norm": 1.0096272230148315,
|
| 1005 |
+
"learning_rate": 3.042212518195051e-06,
|
| 1006 |
+
"loss": 0.0717,
|
| 1007 |
+
"mean_token_accuracy": 0.9340875700116158,
|
| 1008 |
+
"num_tokens": 9082880.0,
|
| 1009 |
+
"step": 1110
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 2.200639291861323,
|
| 1013 |
+
"grad_norm": 0.9769055247306824,
|
| 1014 |
+
"learning_rate": 2.9694323144104806e-06,
|
| 1015 |
+
"loss": 0.0729,
|
| 1016 |
+
"mean_token_accuracy": 0.9370596796274185,
|
| 1017 |
+
"num_tokens": 9164800.0,
|
| 1018 |
+
"step": 1120
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.2203098106712567,
|
| 1022 |
+
"grad_norm": 0.8182367086410522,
|
| 1023 |
+
"learning_rate": 2.8966521106259098e-06,
|
| 1024 |
+
"loss": 0.0714,
|
| 1025 |
+
"mean_token_accuracy": 0.936338060349226,
|
| 1026 |
+
"num_tokens": 9246720.0,
|
| 1027 |
+
"step": 1130
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.23998032948119,
|
| 1031 |
+
"grad_norm": 0.9285300374031067,
|
| 1032 |
+
"learning_rate": 2.8238719068413393e-06,
|
| 1033 |
+
"loss": 0.0717,
|
| 1034 |
+
"mean_token_accuracy": 0.9357020534574986,
|
| 1035 |
+
"num_tokens": 9328640.0,
|
| 1036 |
+
"step": 1140
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 2.2596508482911237,
|
| 1040 |
+
"grad_norm": 0.9658852219581604,
|
| 1041 |
+
"learning_rate": 2.7510917030567684e-06,
|
| 1042 |
+
"loss": 0.0722,
|
| 1043 |
+
"mean_token_accuracy": 0.9356164373457432,
|
| 1044 |
+
"num_tokens": 9410560.0,
|
| 1045 |
+
"step": 1150
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.2793213671010575,
|
| 1049 |
+
"grad_norm": 0.8002274632453918,
|
| 1050 |
+
"learning_rate": 2.678311499272198e-06,
|
| 1051 |
+
"loss": 0.0688,
|
| 1052 |
+
"mean_token_accuracy": 0.9368272982537746,
|
| 1053 |
+
"num_tokens": 9492480.0,
|
| 1054 |
+
"step": 1160
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 2.298991885910991,
|
| 1058 |
+
"grad_norm": 0.7488352060317993,
|
| 1059 |
+
"learning_rate": 2.6055312954876275e-06,
|
| 1060 |
+
"loss": 0.0696,
|
| 1061 |
+
"mean_token_accuracy": 0.9345523476600647,
|
| 1062 |
+
"num_tokens": 9574400.0,
|
| 1063 |
+
"step": 1170
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 2.3186624047209246,
|
| 1067 |
+
"grad_norm": 0.7775608897209167,
|
| 1068 |
+
"learning_rate": 2.5327510917030567e-06,
|
| 1069 |
+
"loss": 0.0701,
|
| 1070 |
+
"mean_token_accuracy": 0.9374877654016018,
|
| 1071 |
+
"num_tokens": 9656320.0,
|
| 1072 |
+
"step": 1180
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 2.3383329235308583,
|
| 1076 |
+
"grad_norm": 0.720152735710144,
|
| 1077 |
+
"learning_rate": 2.4599708879184862e-06,
|
| 1078 |
+
"loss": 0.0686,
|
| 1079 |
+
"mean_token_accuracy": 0.9362769082188607,
|
| 1080 |
+
"num_tokens": 9738240.0,
|
| 1081 |
+
"step": 1190
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.3580034423407916,
|
| 1085 |
+
"grad_norm": 0.8474797010421753,
|
| 1086 |
+
"learning_rate": 2.3871906841339158e-06,
|
| 1087 |
+
"loss": 0.0692,
|
| 1088 |
+
"mean_token_accuracy": 0.9355308227241039,
|
| 1089 |
+
"num_tokens": 9820160.0,
|
| 1090 |
+
"step": 1200
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.3776739611507254,
|
| 1094 |
+
"grad_norm": 0.9920778870582581,
|
| 1095 |
+
"learning_rate": 2.3144104803493453e-06,
|
| 1096 |
+
"loss": 0.0753,
|
| 1097 |
+
"mean_token_accuracy": 0.9328767113387585,
|
| 1098 |
+
"num_tokens": 9902080.0,
|
| 1099 |
+
"step": 1210
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 2.397344479960659,
|
| 1103 |
+
"grad_norm": 0.8659960627555847,
|
| 1104 |
+
"learning_rate": 2.2416302765647744e-06,
|
| 1105 |
+
"loss": 0.0699,
|
| 1106 |
+
"mean_token_accuracy": 0.9354452028870582,
|
| 1107 |
+
"num_tokens": 9984000.0,
|
| 1108 |
+
"step": 1220
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.4170149987705924,
|
| 1112 |
+
"grad_norm": 1.2485941648483276,
|
| 1113 |
+
"learning_rate": 2.168850072780204e-06,
|
| 1114 |
+
"loss": 0.0716,
|
| 1115 |
+
"mean_token_accuracy": 0.9364236779510975,
|
| 1116 |
+
"num_tokens": 10065920.0,
|
| 1117 |
+
"step": 1230
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.436685517580526,
|
| 1121 |
+
"grad_norm": 1.018085241317749,
|
| 1122 |
+
"learning_rate": 2.096069868995633e-06,
|
| 1123 |
+
"loss": 0.0694,
|
| 1124 |
+
"mean_token_accuracy": 0.9354696646332741,
|
| 1125 |
+
"num_tokens": 10147840.0,
|
| 1126 |
+
"step": 1240
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 2.45635603639046,
|
| 1130 |
+
"grad_norm": 0.7919542789459229,
|
| 1131 |
+
"learning_rate": 2.0232896652110627e-06,
|
| 1132 |
+
"loss": 0.0702,
|
| 1133 |
+
"mean_token_accuracy": 0.9352005854249,
|
| 1134 |
+
"num_tokens": 10229760.0,
|
| 1135 |
+
"step": 1250
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.4760265552003933,
|
| 1139 |
+
"grad_norm": 0.7705115079879761,
|
| 1140 |
+
"learning_rate": 1.9505094614264922e-06,
|
| 1141 |
+
"loss": 0.0713,
|
| 1142 |
+
"mean_token_accuracy": 0.93606898188591,
|
| 1143 |
+
"num_tokens": 10311680.0,
|
| 1144 |
+
"step": 1260
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.495697074010327,
|
| 1148 |
+
"grad_norm": 1.0156041383743286,
|
| 1149 |
+
"learning_rate": 1.8777292576419216e-06,
|
| 1150 |
+
"loss": 0.0692,
|
| 1151 |
+
"mean_token_accuracy": 0.9370963759720325,
|
| 1152 |
+
"num_tokens": 10393600.0,
|
| 1153 |
+
"step": 1270
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.515367592820261,
|
| 1157 |
+
"grad_norm": 0.8900818228721619,
|
| 1158 |
+
"learning_rate": 1.8049490538573511e-06,
|
| 1159 |
+
"loss": 0.0719,
|
| 1160 |
+
"mean_token_accuracy": 0.9380381591618061,
|
| 1161 |
+
"num_tokens": 10475520.0,
|
| 1162 |
+
"step": 1280
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 2.535038111630194,
|
| 1166 |
+
"grad_norm": 0.8240485191345215,
|
| 1167 |
+
"learning_rate": 1.7321688500727804e-06,
|
| 1168 |
+
"loss": 0.0691,
|
| 1169 |
+
"mean_token_accuracy": 0.9369985312223434,
|
| 1170 |
+
"num_tokens": 10557440.0,
|
| 1171 |
+
"step": 1290
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.554708630440128,
|
| 1175 |
+
"grad_norm": 1.0211061239242554,
|
| 1176 |
+
"learning_rate": 1.6593886462882098e-06,
|
| 1177 |
+
"loss": 0.0713,
|
| 1178 |
+
"mean_token_accuracy": 0.9360078267753125,
|
| 1179 |
+
"num_tokens": 10639360.0,
|
| 1180 |
+
"step": 1300
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 2.5743791492500616,
|
| 1184 |
+
"grad_norm": 0.8435456156730652,
|
| 1185 |
+
"learning_rate": 1.5866084425036391e-06,
|
| 1186 |
+
"loss": 0.0685,
|
| 1187 |
+
"mean_token_accuracy": 0.9358488261699677,
|
| 1188 |
+
"num_tokens": 10721280.0,
|
| 1189 |
+
"step": 1310
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 2.594049668059995,
|
| 1193 |
+
"grad_norm": 0.7593806982040405,
|
| 1194 |
+
"learning_rate": 1.5138282387190687e-06,
|
| 1195 |
+
"loss": 0.0692,
|
| 1196 |
+
"mean_token_accuracy": 0.9353962808847427,
|
| 1197 |
+
"num_tokens": 10803200.0,
|
| 1198 |
+
"step": 1320
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.6137201868699287,
|
| 1202 |
+
"grad_norm": 0.8326400518417358,
|
| 1203 |
+
"learning_rate": 1.441048034934498e-06,
|
| 1204 |
+
"loss": 0.0722,
|
| 1205 |
+
"mean_token_accuracy": 0.9346868857741356,
|
| 1206 |
+
"num_tokens": 10885120.0,
|
| 1207 |
+
"step": 1330
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.6333907056798624,
|
| 1211 |
+
"grad_norm": 0.8349006772041321,
|
| 1212 |
+
"learning_rate": 1.3682678311499273e-06,
|
| 1213 |
+
"loss": 0.0684,
|
| 1214 |
+
"mean_token_accuracy": 0.9371330693364144,
|
| 1215 |
+
"num_tokens": 10967040.0,
|
| 1216 |
+
"step": 1340
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 2.6530612244897958,
|
| 1220 |
+
"grad_norm": 0.8567010760307312,
|
| 1221 |
+
"learning_rate": 1.2954876273653567e-06,
|
| 1222 |
+
"loss": 0.0707,
|
| 1223 |
+
"mean_token_accuracy": 0.9372064515948295,
|
| 1224 |
+
"num_tokens": 11048960.0,
|
| 1225 |
+
"step": 1350
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 2.6727317432997295,
|
| 1229 |
+
"grad_norm": 1.053802728652954,
|
| 1230 |
+
"learning_rate": 1.222707423580786e-06,
|
| 1231 |
+
"loss": 0.0717,
|
| 1232 |
+
"mean_token_accuracy": 0.9355430543422699,
|
| 1233 |
+
"num_tokens": 11130880.0,
|
| 1234 |
+
"step": 1360
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.6924022621096633,
|
| 1238 |
+
"grad_norm": 1.380603313446045,
|
| 1239 |
+
"learning_rate": 1.1499272197962156e-06,
|
| 1240 |
+
"loss": 0.0673,
|
| 1241 |
+
"mean_token_accuracy": 0.9371942266821861,
|
| 1242 |
+
"num_tokens": 11212800.0,
|
| 1243 |
+
"step": 1370
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 2.7120727809195966,
|
| 1247 |
+
"grad_norm": 1.00258207321167,
|
| 1248 |
+
"learning_rate": 1.077147016011645e-06,
|
| 1249 |
+
"loss": 0.0698,
|
| 1250 |
+
"mean_token_accuracy": 0.9354329757392407,
|
| 1251 |
+
"num_tokens": 11294720.0,
|
| 1252 |
+
"step": 1380
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 2.7317432997295303,
|
| 1256 |
+
"grad_norm": 0.6895238757133484,
|
| 1257 |
+
"learning_rate": 1.0043668122270742e-06,
|
| 1258 |
+
"loss": 0.0696,
|
| 1259 |
+
"mean_token_accuracy": 0.9364481404423713,
|
| 1260 |
+
"num_tokens": 11376640.0,
|
| 1261 |
+
"step": 1390
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 2.751413818539464,
|
| 1265 |
+
"grad_norm": 0.7581794857978821,
|
| 1266 |
+
"learning_rate": 9.315866084425038e-07,
|
| 1267 |
+
"loss": 0.0723,
|
| 1268 |
+
"mean_token_accuracy": 0.9343321897089482,
|
| 1269 |
+
"num_tokens": 11458560.0,
|
| 1270 |
+
"step": 1400
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.7710843373493974,
|
| 1274 |
+
"grad_norm": 0.8926005959510803,
|
| 1275 |
+
"learning_rate": 8.58806404657933e-07,
|
| 1276 |
+
"loss": 0.0712,
|
| 1277 |
+
"mean_token_accuracy": 0.9362157486379147,
|
| 1278 |
+
"num_tokens": 11540480.0,
|
| 1279 |
+
"step": 1410
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 2.790754856159331,
|
| 1283 |
+
"grad_norm": 1.136520504951477,
|
| 1284 |
+
"learning_rate": 7.860262008733626e-07,
|
| 1285 |
+
"loss": 0.07,
|
| 1286 |
+
"mean_token_accuracy": 0.936668298393488,
|
| 1287 |
+
"num_tokens": 11622400.0,
|
| 1288 |
+
"step": 1420
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 2.810425374969265,
|
| 1292 |
+
"grad_norm": 0.910785436630249,
|
| 1293 |
+
"learning_rate": 7.132459970887918e-07,
|
| 1294 |
+
"loss": 0.0669,
|
| 1295 |
+
"mean_token_accuracy": 0.9368028342723846,
|
| 1296 |
+
"num_tokens": 11704320.0,
|
| 1297 |
+
"step": 1430
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.8300958937791982,
|
| 1301 |
+
"grad_norm": 1.0571502447128296,
|
| 1302 |
+
"learning_rate": 6.404657933042214e-07,
|
| 1303 |
+
"loss": 0.072,
|
| 1304 |
+
"mean_token_accuracy": 0.9329623252153396,
|
| 1305 |
+
"num_tokens": 11786240.0,
|
| 1306 |
+
"step": 1440
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.849766412589132,
|
| 1310 |
+
"grad_norm": 0.9572676420211792,
|
| 1311 |
+
"learning_rate": 5.676855895196507e-07,
|
| 1312 |
+
"loss": 0.0723,
|
| 1313 |
+
"mean_token_accuracy": 0.9353106647729874,
|
| 1314 |
+
"num_tokens": 11868160.0,
|
| 1315 |
+
"step": 1450
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 2.8694369313990657,
|
| 1319 |
+
"grad_norm": 1.240408182144165,
|
| 1320 |
+
"learning_rate": 4.949053857350801e-07,
|
| 1321 |
+
"loss": 0.0712,
|
| 1322 |
+
"mean_token_accuracy": 0.9353962816298008,
|
| 1323 |
+
"num_tokens": 11950080.0,
|
| 1324 |
+
"step": 1460
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 2.889107450208999,
|
| 1328 |
+
"grad_norm": 1.247115135192871,
|
| 1329 |
+
"learning_rate": 4.221251819505095e-07,
|
| 1330 |
+
"loss": 0.0706,
|
| 1331 |
+
"mean_token_accuracy": 0.9364236749708652,
|
| 1332 |
+
"num_tokens": 12032000.0,
|
| 1333 |
+
"step": 1470
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.908777969018933,
|
| 1337 |
+
"grad_norm": 0.9491878747940063,
|
| 1338 |
+
"learning_rate": 3.4934497816593887e-07,
|
| 1339 |
+
"loss": 0.0686,
|
| 1340 |
+
"mean_token_accuracy": 0.9364603698253632,
|
| 1341 |
+
"num_tokens": 12113920.0,
|
| 1342 |
+
"step": 1480
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 2.9284484878288666,
|
| 1346 |
+
"grad_norm": 0.7979325652122498,
|
| 1347 |
+
"learning_rate": 2.765647743813683e-07,
|
| 1348 |
+
"loss": 0.0695,
|
| 1349 |
+
"mean_token_accuracy": 0.9378180019557476,
|
| 1350 |
+
"num_tokens": 12195840.0,
|
| 1351 |
+
"step": 1490
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 2.9481190066388,
|
| 1355 |
+
"grad_norm": 0.8599417209625244,
|
| 1356 |
+
"learning_rate": 2.0378457059679768e-07,
|
| 1357 |
+
"loss": 0.0727,
|
| 1358 |
+
"mean_token_accuracy": 0.9342954941093922,
|
| 1359 |
+
"num_tokens": 12277760.0,
|
| 1360 |
+
"step": 1500
|
| 1361 |
}
|
| 1362 |
],
|
| 1363 |
"logging_steps": 10,
|
|
|
|
| 1377 |
"attributes": {}
|
| 1378 |
}
|
| 1379 |
},
|
| 1380 |
+
"total_flos": 3.244772227547136e+16,
|
| 1381 |
"train_batch_size": 2,
|
| 1382 |
"trial_name": null,
|
| 1383 |
"trial_params": null
|