Training in progress, step 4000, 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 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1695d6ce8bd5b7d2355edbbd0898111b45ff3435a1ab08b8365805bc3f3ad00
|
| 3 |
size 223144592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440235130
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f12dff49781fca74d122378f26745ac52fd4b91b3decbb3b980a33448a5411b5
|
| 3 |
size 440235130
|
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:da7113ba4a15f803acd596486d291dff44a22010c3be333f82da6ae49ecda7bd
|
| 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 sha256:21d3eeef439eb9e15103ee606f4a4606b33da69a5d17044fd608528bcb1583fb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./iteboshi_temp/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -877,6 +877,296 @@
|
|
| 877 |
"eval_steps_per_second": 1.17,
|
| 878 |
"eval_wer": 96.64309288071664,
|
| 879 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 880 |
}
|
| 881 |
],
|
| 882 |
"logging_steps": 25,
|
|
@@ -896,7 +1186,7 @@
|
|
| 896 |
"attributes": {}
|
| 897 |
}
|
| 898 |
},
|
| 899 |
-
"total_flos":
|
| 900 |
"train_batch_size": 12,
|
| 901 |
"trial_name": null,
|
| 902 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 95.4926921263555,
|
| 3 |
+
"best_model_checkpoint": "./iteboshi_temp/checkpoint-4000",
|
| 4 |
+
"epoch": 6.601156069364162,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 877 |
"eval_steps_per_second": 1.17,
|
| 878 |
"eval_wer": 96.64309288071664,
|
| 879 |
"step": 3000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 4.992568125516103,
|
| 883 |
+
"grad_norm": 7.915883541107178,
|
| 884 |
+
"learning_rate": 1.4686315789473687e-05,
|
| 885 |
+
"loss": 0.7496,
|
| 886 |
+
"step": 3025
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 5.033030553261767,
|
| 890 |
+
"grad_norm": 7.240871906280518,
|
| 891 |
+
"learning_rate": 1.4633684210526317e-05,
|
| 892 |
+
"loss": 0.687,
|
| 893 |
+
"step": 3050
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 5.074318744838976,
|
| 897 |
+
"grad_norm": 7.480823516845703,
|
| 898 |
+
"learning_rate": 1.4581052631578949e-05,
|
| 899 |
+
"loss": 0.6601,
|
| 900 |
+
"step": 3075
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 5.115606936416185,
|
| 904 |
+
"grad_norm": 7.587548732757568,
|
| 905 |
+
"learning_rate": 1.452842105263158e-05,
|
| 906 |
+
"loss": 0.6831,
|
| 907 |
+
"step": 3100
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 5.156895127993394,
|
| 911 |
+
"grad_norm": 7.099322319030762,
|
| 912 |
+
"learning_rate": 1.4475789473684212e-05,
|
| 913 |
+
"loss": 0.6658,
|
| 914 |
+
"step": 3125
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 5.198183319570603,
|
| 918 |
+
"grad_norm": 7.174043655395508,
|
| 919 |
+
"learning_rate": 1.4423157894736843e-05,
|
| 920 |
+
"loss": 0.6704,
|
| 921 |
+
"step": 3150
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 5.239471511147812,
|
| 925 |
+
"grad_norm": 6.899098873138428,
|
| 926 |
+
"learning_rate": 1.4370526315789475e-05,
|
| 927 |
+
"loss": 0.65,
|
| 928 |
+
"step": 3175
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 5.280759702725021,
|
| 932 |
+
"grad_norm": 7.519511699676514,
|
| 933 |
+
"learning_rate": 1.4317894736842107e-05,
|
| 934 |
+
"loss": 0.6665,
|
| 935 |
+
"step": 3200
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 5.32204789430223,
|
| 939 |
+
"grad_norm": 7.408304214477539,
|
| 940 |
+
"learning_rate": 1.4265263157894738e-05,
|
| 941 |
+
"loss": 0.6398,
|
| 942 |
+
"step": 3225
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 5.363336085879438,
|
| 946 |
+
"grad_norm": 7.133185386657715,
|
| 947 |
+
"learning_rate": 1.4212631578947368e-05,
|
| 948 |
+
"loss": 0.6802,
|
| 949 |
+
"step": 3250
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 5.404624277456647,
|
| 953 |
+
"grad_norm": 7.851741313934326,
|
| 954 |
+
"learning_rate": 1.416e-05,
|
| 955 |
+
"loss": 0.6327,
|
| 956 |
+
"step": 3275
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 5.445912469033856,
|
| 960 |
+
"grad_norm": 7.773444175720215,
|
| 961 |
+
"learning_rate": 1.4107368421052632e-05,
|
| 962 |
+
"loss": 0.6998,
|
| 963 |
+
"step": 3300
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 5.487200660611065,
|
| 967 |
+
"grad_norm": 8.28067398071289,
|
| 968 |
+
"learning_rate": 1.4054736842105263e-05,
|
| 969 |
+
"loss": 0.6726,
|
| 970 |
+
"step": 3325
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 5.528488852188274,
|
| 974 |
+
"grad_norm": 6.886124134063721,
|
| 975 |
+
"learning_rate": 1.4002105263157897e-05,
|
| 976 |
+
"loss": 0.6418,
|
| 977 |
+
"step": 3350
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 5.569777043765483,
|
| 981 |
+
"grad_norm": 6.617015361785889,
|
| 982 |
+
"learning_rate": 1.3949473684210528e-05,
|
| 983 |
+
"loss": 0.6613,
|
| 984 |
+
"step": 3375
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 5.611065235342692,
|
| 988 |
+
"grad_norm": 7.447840690612793,
|
| 989 |
+
"learning_rate": 1.389684210526316e-05,
|
| 990 |
+
"loss": 0.6608,
|
| 991 |
+
"step": 3400
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 5.652353426919901,
|
| 995 |
+
"grad_norm": 7.151592254638672,
|
| 996 |
+
"learning_rate": 1.3844210526315791e-05,
|
| 997 |
+
"loss": 0.6409,
|
| 998 |
+
"step": 3425
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 5.69364161849711,
|
| 1002 |
+
"grad_norm": 7.587296962738037,
|
| 1003 |
+
"learning_rate": 1.3791578947368423e-05,
|
| 1004 |
+
"loss": 0.6483,
|
| 1005 |
+
"step": 3450
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 5.734929810074319,
|
| 1009 |
+
"grad_norm": 7.848781585693359,
|
| 1010 |
+
"learning_rate": 1.3738947368421055e-05,
|
| 1011 |
+
"loss": 0.6638,
|
| 1012 |
+
"step": 3475
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 5.776218001651528,
|
| 1016 |
+
"grad_norm": 7.8602986335754395,
|
| 1017 |
+
"learning_rate": 1.3686315789473685e-05,
|
| 1018 |
+
"loss": 0.6464,
|
| 1019 |
+
"step": 3500
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 5.817506193228737,
|
| 1023 |
+
"grad_norm": 7.792623043060303,
|
| 1024 |
+
"learning_rate": 1.3633684210526316e-05,
|
| 1025 |
+
"loss": 0.6641,
|
| 1026 |
+
"step": 3525
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 5.858794384805946,
|
| 1030 |
+
"grad_norm": 7.796040058135986,
|
| 1031 |
+
"learning_rate": 1.3581052631578948e-05,
|
| 1032 |
+
"loss": 0.6529,
|
| 1033 |
+
"step": 3550
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 5.900082576383154,
|
| 1037 |
+
"grad_norm": 7.527121543884277,
|
| 1038 |
+
"learning_rate": 1.352842105263158e-05,
|
| 1039 |
+
"loss": 0.6458,
|
| 1040 |
+
"step": 3575
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 5.941370767960363,
|
| 1044 |
+
"grad_norm": 6.546653747558594,
|
| 1045 |
+
"learning_rate": 1.3475789473684211e-05,
|
| 1046 |
+
"loss": 0.6087,
|
| 1047 |
+
"step": 3600
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 5.982658959537572,
|
| 1051 |
+
"grad_norm": 8.012529373168945,
|
| 1052 |
+
"learning_rate": 1.3423157894736843e-05,
|
| 1053 |
+
"loss": 0.6298,
|
| 1054 |
+
"step": 3625
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 6.023121387283237,
|
| 1058 |
+
"grad_norm": 7.391585350036621,
|
| 1059 |
+
"learning_rate": 1.3370526315789475e-05,
|
| 1060 |
+
"loss": 0.5543,
|
| 1061 |
+
"step": 3650
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 6.064409578860446,
|
| 1065 |
+
"grad_norm": 6.664039134979248,
|
| 1066 |
+
"learning_rate": 1.3317894736842108e-05,
|
| 1067 |
+
"loss": 0.5252,
|
| 1068 |
+
"step": 3675
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 6.105697770437655,
|
| 1072 |
+
"grad_norm": 6.451517105102539,
|
| 1073 |
+
"learning_rate": 1.326526315789474e-05,
|
| 1074 |
+
"loss": 0.5712,
|
| 1075 |
+
"step": 3700
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 6.146985962014864,
|
| 1079 |
+
"grad_norm": 6.391648292541504,
|
| 1080 |
+
"learning_rate": 1.321263157894737e-05,
|
| 1081 |
+
"loss": 0.5664,
|
| 1082 |
+
"step": 3725
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 6.188274153592072,
|
| 1086 |
+
"grad_norm": 6.524181842803955,
|
| 1087 |
+
"learning_rate": 1.3160000000000001e-05,
|
| 1088 |
+
"loss": 0.5514,
|
| 1089 |
+
"step": 3750
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 6.229562345169281,
|
| 1093 |
+
"grad_norm": 6.788370609283447,
|
| 1094 |
+
"learning_rate": 1.3107368421052633e-05,
|
| 1095 |
+
"loss": 0.5693,
|
| 1096 |
+
"step": 3775
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 6.27085053674649,
|
| 1100 |
+
"grad_norm": 6.802549839019775,
|
| 1101 |
+
"learning_rate": 1.3054736842105264e-05,
|
| 1102 |
+
"loss": 0.5332,
|
| 1103 |
+
"step": 3800
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 6.312138728323699,
|
| 1107 |
+
"grad_norm": 6.864429473876953,
|
| 1108 |
+
"learning_rate": 1.3002105263157896e-05,
|
| 1109 |
+
"loss": 0.5582,
|
| 1110 |
+
"step": 3825
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 6.353426919900908,
|
| 1114 |
+
"grad_norm": 7.168697357177734,
|
| 1115 |
+
"learning_rate": 1.2949473684210528e-05,
|
| 1116 |
+
"loss": 0.5471,
|
| 1117 |
+
"step": 3850
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 6.394715111478117,
|
| 1121 |
+
"grad_norm": 6.500988960266113,
|
| 1122 |
+
"learning_rate": 1.289684210526316e-05,
|
| 1123 |
+
"loss": 0.5472,
|
| 1124 |
+
"step": 3875
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 6.436003303055326,
|
| 1128 |
+
"grad_norm": 6.378172874450684,
|
| 1129 |
+
"learning_rate": 1.2844210526315791e-05,
|
| 1130 |
+
"loss": 0.5512,
|
| 1131 |
+
"step": 3900
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 6.477291494632535,
|
| 1135 |
+
"grad_norm": 6.865861415863037,
|
| 1136 |
+
"learning_rate": 1.279157894736842e-05,
|
| 1137 |
+
"loss": 0.5739,
|
| 1138 |
+
"step": 3925
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 6.518579686209744,
|
| 1142 |
+
"grad_norm": 6.929198741912842,
|
| 1143 |
+
"learning_rate": 1.2738947368421052e-05,
|
| 1144 |
+
"loss": 0.5654,
|
| 1145 |
+
"step": 3950
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 6.559867877786953,
|
| 1149 |
+
"grad_norm": 6.951797008514404,
|
| 1150 |
+
"learning_rate": 1.2686315789473684e-05,
|
| 1151 |
+
"loss": 0.5422,
|
| 1152 |
+
"step": 3975
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 6.601156069364162,
|
| 1156 |
+
"grad_norm": 7.957674980163574,
|
| 1157 |
+
"learning_rate": 1.2633684210526316e-05,
|
| 1158 |
+
"loss": 0.5464,
|
| 1159 |
+
"step": 4000
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 6.601156069364162,
|
| 1163 |
+
"eval_cer": 48.25066202010707,
|
| 1164 |
+
"eval_loss": 1.0574802160263062,
|
| 1165 |
+
"eval_runtime": 742.515,
|
| 1166 |
+
"eval_samples_per_second": 14.25,
|
| 1167 |
+
"eval_steps_per_second": 1.188,
|
| 1168 |
+
"eval_wer": 95.4926921263555,
|
| 1169 |
+
"step": 4000
|
| 1170 |
}
|
| 1171 |
],
|
| 1172 |
"logging_steps": 25,
|
|
|
|
| 1186 |
"attributes": {}
|
| 1187 |
}
|
| 1188 |
},
|
| 1189 |
+
"total_flos": 7.79712372670464e+18,
|
| 1190 |
"train_batch_size": 12,
|
| 1191 |
"trial_name": null,
|
| 1192 |
"trial_params": null
|