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 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b35281e57f38653ec64c5bc5be60610b3bddf528283e52b17f94b101f0da1e3
|
| 3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1925064044
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7dd151efea5d7680180e1189346e1df7c2dcb8e0a5fa46b8d2fff36f69f4ca9
|
| 3 |
size 1925064044
|
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:d4a887c0679a244fb3578da62fc4230274c5d38de547b25494a50298ffcd112e
|
| 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 sha256:9b52ab14c4ce453c2751c4f86099cc9afc680226047a17acc9c5c9e00c75b7d9
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 51.
|
| 3 |
-
"best_model_checkpoint": "./whisper-small-taiwanese/checkpoint-
|
| 4 |
-
"epoch": 1.
|
| 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,
|
|
@@ -874,6 +874,295 @@
|
|
| 874 |
"eval_samples_per_second": 2.202,
|
| 875 |
"eval_steps_per_second": 0.275,
|
| 876 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 877 |
}
|
| 878 |
],
|
| 879 |
"logging_steps": 25,
|
|
@@ -881,7 +1170,7 @@
|
|
| 881 |
"num_input_tokens_seen": 0,
|
| 882 |
"num_train_epochs": 2,
|
| 883 |
"save_steps": 1000,
|
| 884 |
-
"total_flos": 1.
|
| 885 |
"train_batch_size": 8,
|
| 886 |
"trial_name": null,
|
| 887 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 51.82156133828997,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-taiwanese/checkpoint-4000",
|
| 4 |
+
"epoch": 1.6009605763458075,
|
| 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,
|
|
|
|
| 874 |
"eval_samples_per_second": 2.202,
|
| 875 |
"eval_steps_per_second": 0.275,
|
| 876 |
"step": 3000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.2107264358615168,
|
| 880 |
+
"grad_norm": 10.6748628616333,
|
| 881 |
+
"learning_rate": 4.383896797153026e-06,
|
| 882 |
+
"loss": 0.7877,
|
| 883 |
+
"step": 3025
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.2207324394636783,
|
| 887 |
+
"grad_norm": 11.652464866638184,
|
| 888 |
+
"learning_rate": 4.328291814946619e-06,
|
| 889 |
+
"loss": 0.7794,
|
| 890 |
+
"step": 3050
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.2307384430658395,
|
| 894 |
+
"grad_norm": 11.998939514160156,
|
| 895 |
+
"learning_rate": 4.272686832740214e-06,
|
| 896 |
+
"loss": 0.8183,
|
| 897 |
+
"step": 3075
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.2407444466680009,
|
| 901 |
+
"grad_norm": 13.142699241638184,
|
| 902 |
+
"learning_rate": 4.217081850533808e-06,
|
| 903 |
+
"loss": 0.7834,
|
| 904 |
+
"step": 3100
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.250750450270162,
|
| 908 |
+
"grad_norm": 11.67496395111084,
|
| 909 |
+
"learning_rate": 4.161476868327402e-06,
|
| 910 |
+
"loss": 0.7594,
|
| 911 |
+
"step": 3125
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.2607564538723235,
|
| 915 |
+
"grad_norm": 11.429244995117188,
|
| 916 |
+
"learning_rate": 4.105871886120997e-06,
|
| 917 |
+
"loss": 0.7963,
|
| 918 |
+
"step": 3150
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 1.2707624574744847,
|
| 922 |
+
"grad_norm": 12.160046577453613,
|
| 923 |
+
"learning_rate": 4.0502669039145905e-06,
|
| 924 |
+
"loss": 0.7441,
|
| 925 |
+
"step": 3175
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 1.2807684610766459,
|
| 929 |
+
"grad_norm": 12.606410026550293,
|
| 930 |
+
"learning_rate": 3.994661921708186e-06,
|
| 931 |
+
"loss": 0.8733,
|
| 932 |
+
"step": 3200
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.2907744646788073,
|
| 936 |
+
"grad_norm": 14.263989448547363,
|
| 937 |
+
"learning_rate": 3.93905693950178e-06,
|
| 938 |
+
"loss": 0.7433,
|
| 939 |
+
"step": 3225
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.3007804682809687,
|
| 943 |
+
"grad_norm": 11.299212455749512,
|
| 944 |
+
"learning_rate": 3.883451957295374e-06,
|
| 945 |
+
"loss": 0.789,
|
| 946 |
+
"step": 3250
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.31078647188313,
|
| 950 |
+
"grad_norm": 12.999605178833008,
|
| 951 |
+
"learning_rate": 3.827846975088969e-06,
|
| 952 |
+
"loss": 0.7868,
|
| 953 |
+
"step": 3275
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.320792475485291,
|
| 957 |
+
"grad_norm": 10.38305950164795,
|
| 958 |
+
"learning_rate": 3.7722419928825625e-06,
|
| 959 |
+
"loss": 0.7433,
|
| 960 |
+
"step": 3300
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.3307984790874525,
|
| 964 |
+
"grad_norm": 13.05246639251709,
|
| 965 |
+
"learning_rate": 3.7166370106761567e-06,
|
| 966 |
+
"loss": 0.7547,
|
| 967 |
+
"step": 3325
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 1.3408044826896137,
|
| 971 |
+
"grad_norm": 11.195088386535645,
|
| 972 |
+
"learning_rate": 3.661032028469751e-06,
|
| 973 |
+
"loss": 0.8126,
|
| 974 |
+
"step": 3350
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.3508104862917751,
|
| 978 |
+
"grad_norm": 11.096240997314453,
|
| 979 |
+
"learning_rate": 3.605427046263346e-06,
|
| 980 |
+
"loss": 0.743,
|
| 981 |
+
"step": 3375
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.3608164898939363,
|
| 985 |
+
"grad_norm": 13.594226837158203,
|
| 986 |
+
"learning_rate": 3.5498220640569395e-06,
|
| 987 |
+
"loss": 0.7965,
|
| 988 |
+
"step": 3400
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.3708224934960977,
|
| 992 |
+
"grad_norm": 15.316413879394531,
|
| 993 |
+
"learning_rate": 3.4942170818505337e-06,
|
| 994 |
+
"loss": 0.7956,
|
| 995 |
+
"step": 3425
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.380828497098259,
|
| 999 |
+
"grad_norm": 12.78977108001709,
|
| 1000 |
+
"learning_rate": 3.4386120996441287e-06,
|
| 1001 |
+
"loss": 0.7693,
|
| 1002 |
+
"step": 3450
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.3908345007004201,
|
| 1006 |
+
"grad_norm": 12.662712097167969,
|
| 1007 |
+
"learning_rate": 3.383007117437723e-06,
|
| 1008 |
+
"loss": 0.7768,
|
| 1009 |
+
"step": 3475
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.4008405043025816,
|
| 1013 |
+
"grad_norm": 8.803949356079102,
|
| 1014 |
+
"learning_rate": 3.327402135231317e-06,
|
| 1015 |
+
"loss": 0.7622,
|
| 1016 |
+
"step": 3500
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.410846507904743,
|
| 1020 |
+
"grad_norm": 13.736053466796875,
|
| 1021 |
+
"learning_rate": 3.2717971530249116e-06,
|
| 1022 |
+
"loss": 0.8152,
|
| 1023 |
+
"step": 3525
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.4208525115069042,
|
| 1027 |
+
"grad_norm": 12.255024909973145,
|
| 1028 |
+
"learning_rate": 3.2161921708185057e-06,
|
| 1029 |
+
"loss": 0.8149,
|
| 1030 |
+
"step": 3550
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.4308585151090654,
|
| 1034 |
+
"grad_norm": 12.75201416015625,
|
| 1035 |
+
"learning_rate": 3.1605871886121e-06,
|
| 1036 |
+
"loss": 0.7471,
|
| 1037 |
+
"step": 3575
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.4408645187112268,
|
| 1041 |
+
"grad_norm": 13.30036449432373,
|
| 1042 |
+
"learning_rate": 3.1049822064056944e-06,
|
| 1043 |
+
"loss": 0.6892,
|
| 1044 |
+
"step": 3600
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.450870522313388,
|
| 1048 |
+
"grad_norm": 10.946511268615723,
|
| 1049 |
+
"learning_rate": 3.0493772241992886e-06,
|
| 1050 |
+
"loss": 0.7916,
|
| 1051 |
+
"step": 3625
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.4608765259155494,
|
| 1055 |
+
"grad_norm": 10.852522850036621,
|
| 1056 |
+
"learning_rate": 2.9937722419928827e-06,
|
| 1057 |
+
"loss": 0.7329,
|
| 1058 |
+
"step": 3650
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.4708825295177106,
|
| 1062 |
+
"grad_norm": 11.466883659362793,
|
| 1063 |
+
"learning_rate": 2.938167259786477e-06,
|
| 1064 |
+
"loss": 0.7588,
|
| 1065 |
+
"step": 3675
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.480888533119872,
|
| 1069 |
+
"grad_norm": 12.728093147277832,
|
| 1070 |
+
"learning_rate": 2.8825622775800715e-06,
|
| 1071 |
+
"loss": 0.7527,
|
| 1072 |
+
"step": 3700
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.4908945367220332,
|
| 1076 |
+
"grad_norm": 9.343868255615234,
|
| 1077 |
+
"learning_rate": 2.8269572953736656e-06,
|
| 1078 |
+
"loss": 0.7451,
|
| 1079 |
+
"step": 3725
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.5009005403241944,
|
| 1083 |
+
"grad_norm": 14.047112464904785,
|
| 1084 |
+
"learning_rate": 2.7713523131672598e-06,
|
| 1085 |
+
"loss": 0.7905,
|
| 1086 |
+
"step": 3750
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.5109065439263558,
|
| 1090 |
+
"grad_norm": 10.599916458129883,
|
| 1091 |
+
"learning_rate": 2.7157473309608543e-06,
|
| 1092 |
+
"loss": 0.7819,
|
| 1093 |
+
"step": 3775
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.5209125475285172,
|
| 1097 |
+
"grad_norm": 14.341135025024414,
|
| 1098 |
+
"learning_rate": 2.6601423487544485e-06,
|
| 1099 |
+
"loss": 0.7166,
|
| 1100 |
+
"step": 3800
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.5309185511306784,
|
| 1104 |
+
"grad_norm": 11.71387767791748,
|
| 1105 |
+
"learning_rate": 2.6045373665480426e-06,
|
| 1106 |
+
"loss": 0.7386,
|
| 1107 |
+
"step": 3825
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.5409245547328396,
|
| 1111 |
+
"grad_norm": 12.604011535644531,
|
| 1112 |
+
"learning_rate": 2.5489323843416376e-06,
|
| 1113 |
+
"loss": 0.6969,
|
| 1114 |
+
"step": 3850
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.550930558335001,
|
| 1118 |
+
"grad_norm": 9.848773002624512,
|
| 1119 |
+
"learning_rate": 2.4933274021352318e-06,
|
| 1120 |
+
"loss": 0.8356,
|
| 1121 |
+
"step": 3875
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.5609365619371625,
|
| 1125 |
+
"grad_norm": 14.05534553527832,
|
| 1126 |
+
"learning_rate": 2.437722419928826e-06,
|
| 1127 |
+
"loss": 0.7282,
|
| 1128 |
+
"step": 3900
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 1.5709425655393234,
|
| 1132 |
+
"grad_norm": 12.9791259765625,
|
| 1133 |
+
"learning_rate": 2.38211743772242e-06,
|
| 1134 |
+
"loss": 0.7059,
|
| 1135 |
+
"step": 3925
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 1.5809485691414848,
|
| 1139 |
+
"grad_norm": 10.708452224731445,
|
| 1140 |
+
"learning_rate": 2.3265124555160142e-06,
|
| 1141 |
+
"loss": 0.7712,
|
| 1142 |
+
"step": 3950
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 1.5909545727436463,
|
| 1146 |
+
"grad_norm": 13.361218452453613,
|
| 1147 |
+
"learning_rate": 2.270907473309609e-06,
|
| 1148 |
+
"loss": 0.719,
|
| 1149 |
+
"step": 3975
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.6009605763458075,
|
| 1153 |
+
"grad_norm": 11.740647315979004,
|
| 1154 |
+
"learning_rate": 2.215302491103203e-06,
|
| 1155 |
+
"loss": 0.8262,
|
| 1156 |
+
"step": 4000
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 1.6009605763458075,
|
| 1160 |
+
"eval_cer": 51.82156133828997,
|
| 1161 |
+
"eval_loss": 0.9109482169151306,
|
| 1162 |
+
"eval_runtime": 1918.0204,
|
| 1163 |
+
"eval_samples_per_second": 2.068,
|
| 1164 |
+
"eval_steps_per_second": 0.259,
|
| 1165 |
+
"step": 4000
|
| 1166 |
}
|
| 1167 |
],
|
| 1168 |
"logging_steps": 25,
|
|
|
|
| 1170 |
"num_input_tokens_seen": 0,
|
| 1171 |
"num_train_epochs": 2,
|
| 1172 |
"save_steps": 1000,
|
| 1173 |
+
"total_flos": 1.846744552267776e+19,
|
| 1174 |
"train_batch_size": 8,
|
| 1175 |
"trial_name": null,
|
| 1176 |
"trial_params": null
|