Training in progress, step 52000, checkpoint
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +353 -3
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 304481530
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25009f43aad76e069c954daa3d47d4ca26504c93442dee2ee643e9986effa50e
|
| 3 |
size 304481530
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 402029570
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dabedc4ac920e0e51d9510c26d28fe51389ca84a3b20b22845f282b75b7c544
|
| 3 |
size 402029570
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db4bee81e6530bb38ac2be30339582f8d8e268e22071510ef68e8cc5fc22eee7
|
| 3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8789ee656d25337c398ba584b49a55d7717d7d8c4b6da34526139fda7dce6f5
|
| 3 |
size 14960
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd0a9d3fa657314e26df75e7fa11d8377b678420c97c124ef02a79022b3d2358
|
| 3 |
size 14960
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f42244579cef1f142684432be4b616deb856b8430e92719e60b4fa8b30345ac5
|
| 3 |
size 14960
|
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 sha256:9948379edb2ae231aacd92fa9d3b4ab412c6756f9dd9b04618a3eccf04ef2931
|
| 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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -17858,6 +17858,356 @@
|
|
| 17858 |
"learning_rate": 0.0004875294360526451,
|
| 17859 |
"loss": 17.377,
|
| 17860 |
"step": 51000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17861 |
}
|
| 17862 |
],
|
| 17863 |
"logging_steps": 20,
|
|
@@ -17877,7 +18227,7 @@
|
|
| 17877 |
"attributes": {}
|
| 17878 |
}
|
| 17879 |
},
|
| 17880 |
-
"total_flos": 3.
|
| 17881 |
"train_batch_size": 48,
|
| 17882 |
"trial_name": null,
|
| 17883 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.07702836421380704,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 52000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17858 |
"learning_rate": 0.0004875294360526451,
|
| 17859 |
"loss": 17.377,
|
| 17860 |
"step": 51000
|
| 17861 |
+
},
|
| 17862 |
+
{
|
| 17863 |
+
"epoch": 0.07557667581131607,
|
| 17864 |
+
"grad_norm": 6.90625,
|
| 17865 |
+
"learning_rate": 0.0004875244971176375,
|
| 17866 |
+
"loss": 17.431,
|
| 17867 |
+
"step": 51020
|
| 17868 |
+
},
|
| 17869 |
+
{
|
| 17870 |
+
"epoch": 0.07560630210524445,
|
| 17871 |
+
"grad_norm": 7.125,
|
| 17872 |
+
"learning_rate": 0.00048751955818263,
|
| 17873 |
+
"loss": 17.3491,
|
| 17874 |
+
"step": 51040
|
| 17875 |
+
},
|
| 17876 |
+
{
|
| 17877 |
+
"epoch": 0.07563592839917284,
|
| 17878 |
+
"grad_norm": 7.53125,
|
| 17879 |
+
"learning_rate": 0.0004875146192476224,
|
| 17880 |
+
"loss": 17.3375,
|
| 17881 |
+
"step": 51060
|
| 17882 |
+
},
|
| 17883 |
+
{
|
| 17884 |
+
"epoch": 0.07566555469310123,
|
| 17885 |
+
"grad_norm": 7.75,
|
| 17886 |
+
"learning_rate": 0.00048750968031261485,
|
| 17887 |
+
"loss": 17.3697,
|
| 17888 |
+
"step": 51080
|
| 17889 |
+
},
|
| 17890 |
+
{
|
| 17891 |
+
"epoch": 0.07569518098702961,
|
| 17892 |
+
"grad_norm": 7.6875,
|
| 17893 |
+
"learning_rate": 0.00048750474137760724,
|
| 17894 |
+
"loss": 17.4036,
|
| 17895 |
+
"step": 51100
|
| 17896 |
+
},
|
| 17897 |
+
{
|
| 17898 |
+
"epoch": 0.075724807280958,
|
| 17899 |
+
"grad_norm": 6.0,
|
| 17900 |
+
"learning_rate": 0.00048749980244259974,
|
| 17901 |
+
"loss": 17.3631,
|
| 17902 |
+
"step": 51120
|
| 17903 |
+
},
|
| 17904 |
+
{
|
| 17905 |
+
"epoch": 0.07575443357488638,
|
| 17906 |
+
"grad_norm": 6.875,
|
| 17907 |
+
"learning_rate": 0.00048749486350759214,
|
| 17908 |
+
"loss": 17.3267,
|
| 17909 |
+
"step": 51140
|
| 17910 |
+
},
|
| 17911 |
+
{
|
| 17912 |
+
"epoch": 0.07578405986881477,
|
| 17913 |
+
"grad_norm": 6.78125,
|
| 17914 |
+
"learning_rate": 0.0004874899245725846,
|
| 17915 |
+
"loss": 17.353,
|
| 17916 |
+
"step": 51160
|
| 17917 |
+
},
|
| 17918 |
+
{
|
| 17919 |
+
"epoch": 0.07581368616274316,
|
| 17920 |
+
"grad_norm": 6.5625,
|
| 17921 |
+
"learning_rate": 0.000487484985637577,
|
| 17922 |
+
"loss": 17.3355,
|
| 17923 |
+
"step": 51180
|
| 17924 |
+
},
|
| 17925 |
+
{
|
| 17926 |
+
"epoch": 0.07584331245667154,
|
| 17927 |
+
"grad_norm": 6.625,
|
| 17928 |
+
"learning_rate": 0.0004874800467025695,
|
| 17929 |
+
"loss": 17.3533,
|
| 17930 |
+
"step": 51200
|
| 17931 |
+
},
|
| 17932 |
+
{
|
| 17933 |
+
"epoch": 0.07587293875059993,
|
| 17934 |
+
"grad_norm": 6.90625,
|
| 17935 |
+
"learning_rate": 0.0004874751077675619,
|
| 17936 |
+
"loss": 17.2867,
|
| 17937 |
+
"step": 51220
|
| 17938 |
+
},
|
| 17939 |
+
{
|
| 17940 |
+
"epoch": 0.07590256504452832,
|
| 17941 |
+
"grad_norm": 7.4375,
|
| 17942 |
+
"learning_rate": 0.0004874701688325543,
|
| 17943 |
+
"loss": 17.3874,
|
| 17944 |
+
"step": 51240
|
| 17945 |
+
},
|
| 17946 |
+
{
|
| 17947 |
+
"epoch": 0.0759321913384567,
|
| 17948 |
+
"grad_norm": 7.03125,
|
| 17949 |
+
"learning_rate": 0.00048746522989754677,
|
| 17950 |
+
"loss": 17.3779,
|
| 17951 |
+
"step": 51260
|
| 17952 |
+
},
|
| 17953 |
+
{
|
| 17954 |
+
"epoch": 0.07596181763238509,
|
| 17955 |
+
"grad_norm": 6.75,
|
| 17956 |
+
"learning_rate": 0.00048746029096253916,
|
| 17957 |
+
"loss": 17.2991,
|
| 17958 |
+
"step": 51280
|
| 17959 |
+
},
|
| 17960 |
+
{
|
| 17961 |
+
"epoch": 0.07599144392631348,
|
| 17962 |
+
"grad_norm": 6.75,
|
| 17963 |
+
"learning_rate": 0.0004874553520275316,
|
| 17964 |
+
"loss": 17.3238,
|
| 17965 |
+
"step": 51300
|
| 17966 |
+
},
|
| 17967 |
+
{
|
| 17968 |
+
"epoch": 0.07602107022024186,
|
| 17969 |
+
"grad_norm": 7.34375,
|
| 17970 |
+
"learning_rate": 0.000487450413092524,
|
| 17971 |
+
"loss": 17.3291,
|
| 17972 |
+
"step": 51320
|
| 17973 |
+
},
|
| 17974 |
+
{
|
| 17975 |
+
"epoch": 0.07605069651417026,
|
| 17976 |
+
"grad_norm": 6.53125,
|
| 17977 |
+
"learning_rate": 0.0004874454741575165,
|
| 17978 |
+
"loss": 17.3827,
|
| 17979 |
+
"step": 51340
|
| 17980 |
+
},
|
| 17981 |
+
{
|
| 17982 |
+
"epoch": 0.07608032280809865,
|
| 17983 |
+
"grad_norm": 7.46875,
|
| 17984 |
+
"learning_rate": 0.0004874405352225089,
|
| 17985 |
+
"loss": 17.3967,
|
| 17986 |
+
"step": 51360
|
| 17987 |
+
},
|
| 17988 |
+
{
|
| 17989 |
+
"epoch": 0.07610994910202704,
|
| 17990 |
+
"grad_norm": 6.375,
|
| 17991 |
+
"learning_rate": 0.00048743559628750135,
|
| 17992 |
+
"loss": 17.2831,
|
| 17993 |
+
"step": 51380
|
| 17994 |
+
},
|
| 17995 |
+
{
|
| 17996 |
+
"epoch": 0.07613957539595542,
|
| 17997 |
+
"grad_norm": 7.09375,
|
| 17998 |
+
"learning_rate": 0.00048743065735249374,
|
| 17999 |
+
"loss": 17.3631,
|
| 18000 |
+
"step": 51400
|
| 18001 |
+
},
|
| 18002 |
+
{
|
| 18003 |
+
"epoch": 0.07616920168988381,
|
| 18004 |
+
"grad_norm": 7.125,
|
| 18005 |
+
"learning_rate": 0.00048742571841748624,
|
| 18006 |
+
"loss": 17.3253,
|
| 18007 |
+
"step": 51420
|
| 18008 |
+
},
|
| 18009 |
+
{
|
| 18010 |
+
"epoch": 0.0761988279838122,
|
| 18011 |
+
"grad_norm": 6.65625,
|
| 18012 |
+
"learning_rate": 0.00048742077948247864,
|
| 18013 |
+
"loss": 17.3055,
|
| 18014 |
+
"step": 51440
|
| 18015 |
+
},
|
| 18016 |
+
{
|
| 18017 |
+
"epoch": 0.07622845427774058,
|
| 18018 |
+
"grad_norm": 6.625,
|
| 18019 |
+
"learning_rate": 0.0004874158405474711,
|
| 18020 |
+
"loss": 17.2605,
|
| 18021 |
+
"step": 51460
|
| 18022 |
+
},
|
| 18023 |
+
{
|
| 18024 |
+
"epoch": 0.07625808057166897,
|
| 18025 |
+
"grad_norm": 6.8125,
|
| 18026 |
+
"learning_rate": 0.0004874109016124635,
|
| 18027 |
+
"loss": 17.3248,
|
| 18028 |
+
"step": 51480
|
| 18029 |
+
},
|
| 18030 |
+
{
|
| 18031 |
+
"epoch": 0.07628770686559735,
|
| 18032 |
+
"grad_norm": 7.75,
|
| 18033 |
+
"learning_rate": 0.000487405962677456,
|
| 18034 |
+
"loss": 17.3097,
|
| 18035 |
+
"step": 51500
|
| 18036 |
+
},
|
| 18037 |
+
{
|
| 18038 |
+
"epoch": 0.07631733315952574,
|
| 18039 |
+
"grad_norm": 7.40625,
|
| 18040 |
+
"learning_rate": 0.0004874010237424484,
|
| 18041 |
+
"loss": 17.3779,
|
| 18042 |
+
"step": 51520
|
| 18043 |
+
},
|
| 18044 |
+
{
|
| 18045 |
+
"epoch": 0.07634695945345413,
|
| 18046 |
+
"grad_norm": 6.8125,
|
| 18047 |
+
"learning_rate": 0.0004873960848074408,
|
| 18048 |
+
"loss": 17.3135,
|
| 18049 |
+
"step": 51540
|
| 18050 |
+
},
|
| 18051 |
+
{
|
| 18052 |
+
"epoch": 0.07637658574738251,
|
| 18053 |
+
"grad_norm": 7.0625,
|
| 18054 |
+
"learning_rate": 0.00048739114587243327,
|
| 18055 |
+
"loss": 17.3131,
|
| 18056 |
+
"step": 51560
|
| 18057 |
+
},
|
| 18058 |
+
{
|
| 18059 |
+
"epoch": 0.0764062120413109,
|
| 18060 |
+
"grad_norm": 6.9375,
|
| 18061 |
+
"learning_rate": 0.0004873862069374257,
|
| 18062 |
+
"loss": 17.3324,
|
| 18063 |
+
"step": 51580
|
| 18064 |
+
},
|
| 18065 |
+
{
|
| 18066 |
+
"epoch": 0.07643583833523929,
|
| 18067 |
+
"grad_norm": 7.96875,
|
| 18068 |
+
"learning_rate": 0.0004873812680024181,
|
| 18069 |
+
"loss": 17.2835,
|
| 18070 |
+
"step": 51600
|
| 18071 |
+
},
|
| 18072 |
+
{
|
| 18073 |
+
"epoch": 0.07646546462916767,
|
| 18074 |
+
"grad_norm": 6.78125,
|
| 18075 |
+
"learning_rate": 0.0004873763290674105,
|
| 18076 |
+
"loss": 17.3365,
|
| 18077 |
+
"step": 51620
|
| 18078 |
+
},
|
| 18079 |
+
{
|
| 18080 |
+
"epoch": 0.07649509092309606,
|
| 18081 |
+
"grad_norm": 8.3125,
|
| 18082 |
+
"learning_rate": 0.000487371390132403,
|
| 18083 |
+
"loss": 17.3028,
|
| 18084 |
+
"step": 51640
|
| 18085 |
+
},
|
| 18086 |
+
{
|
| 18087 |
+
"epoch": 0.07652471721702446,
|
| 18088 |
+
"grad_norm": 6.9375,
|
| 18089 |
+
"learning_rate": 0.0004873664511973954,
|
| 18090 |
+
"loss": 17.3042,
|
| 18091 |
+
"step": 51660
|
| 18092 |
+
},
|
| 18093 |
+
{
|
| 18094 |
+
"epoch": 0.07655434351095285,
|
| 18095 |
+
"grad_norm": 7.09375,
|
| 18096 |
+
"learning_rate": 0.00048736151226238785,
|
| 18097 |
+
"loss": 17.2441,
|
| 18098 |
+
"step": 51680
|
| 18099 |
+
},
|
| 18100 |
+
{
|
| 18101 |
+
"epoch": 0.07658396980488123,
|
| 18102 |
+
"grad_norm": 7.25,
|
| 18103 |
+
"learning_rate": 0.00048735657332738024,
|
| 18104 |
+
"loss": 17.2984,
|
| 18105 |
+
"step": 51700
|
| 18106 |
+
},
|
| 18107 |
+
{
|
| 18108 |
+
"epoch": 0.07661359609880962,
|
| 18109 |
+
"grad_norm": 7.5,
|
| 18110 |
+
"learning_rate": 0.00048735163439237274,
|
| 18111 |
+
"loss": 17.3066,
|
| 18112 |
+
"step": 51720
|
| 18113 |
+
},
|
| 18114 |
+
{
|
| 18115 |
+
"epoch": 0.076643222392738,
|
| 18116 |
+
"grad_norm": 6.21875,
|
| 18117 |
+
"learning_rate": 0.00048734669545736514,
|
| 18118 |
+
"loss": 17.3059,
|
| 18119 |
+
"step": 51740
|
| 18120 |
+
},
|
| 18121 |
+
{
|
| 18122 |
+
"epoch": 0.07667284868666639,
|
| 18123 |
+
"grad_norm": 6.84375,
|
| 18124 |
+
"learning_rate": 0.0004873417565223576,
|
| 18125 |
+
"loss": 17.323,
|
| 18126 |
+
"step": 51760
|
| 18127 |
+
},
|
| 18128 |
+
{
|
| 18129 |
+
"epoch": 0.07670247498059478,
|
| 18130 |
+
"grad_norm": 6.75,
|
| 18131 |
+
"learning_rate": 0.00048733681758735,
|
| 18132 |
+
"loss": 17.3962,
|
| 18133 |
+
"step": 51780
|
| 18134 |
+
},
|
| 18135 |
+
{
|
| 18136 |
+
"epoch": 0.07673210127452317,
|
| 18137 |
+
"grad_norm": 7.125,
|
| 18138 |
+
"learning_rate": 0.0004873318786523425,
|
| 18139 |
+
"loss": 17.3256,
|
| 18140 |
+
"step": 51800
|
| 18141 |
+
},
|
| 18142 |
+
{
|
| 18143 |
+
"epoch": 0.07676172756845155,
|
| 18144 |
+
"grad_norm": 6.46875,
|
| 18145 |
+
"learning_rate": 0.0004873269397173349,
|
| 18146 |
+
"loss": 17.2537,
|
| 18147 |
+
"step": 51820
|
| 18148 |
+
},
|
| 18149 |
+
{
|
| 18150 |
+
"epoch": 0.07679135386237994,
|
| 18151 |
+
"grad_norm": 6.6875,
|
| 18152 |
+
"learning_rate": 0.0004873220007823273,
|
| 18153 |
+
"loss": 17.2684,
|
| 18154 |
+
"step": 51840
|
| 18155 |
+
},
|
| 18156 |
+
{
|
| 18157 |
+
"epoch": 0.07682098015630832,
|
| 18158 |
+
"grad_norm": 6.59375,
|
| 18159 |
+
"learning_rate": 0.00048731706184731977,
|
| 18160 |
+
"loss": 17.2797,
|
| 18161 |
+
"step": 51860
|
| 18162 |
+
},
|
| 18163 |
+
{
|
| 18164 |
+
"epoch": 0.07685060645023671,
|
| 18165 |
+
"grad_norm": 7.0,
|
| 18166 |
+
"learning_rate": 0.0004873121229123122,
|
| 18167 |
+
"loss": 17.3257,
|
| 18168 |
+
"step": 51880
|
| 18169 |
+
},
|
| 18170 |
+
{
|
| 18171 |
+
"epoch": 0.0768802327441651,
|
| 18172 |
+
"grad_norm": 6.65625,
|
| 18173 |
+
"learning_rate": 0.0004873071839773046,
|
| 18174 |
+
"loss": 17.3123,
|
| 18175 |
+
"step": 51900
|
| 18176 |
+
},
|
| 18177 |
+
{
|
| 18178 |
+
"epoch": 0.07690985903809348,
|
| 18179 |
+
"grad_norm": 7.125,
|
| 18180 |
+
"learning_rate": 0.00048730224504229706,
|
| 18181 |
+
"loss": 17.3099,
|
| 18182 |
+
"step": 51920
|
| 18183 |
+
},
|
| 18184 |
+
{
|
| 18185 |
+
"epoch": 0.07693948533202187,
|
| 18186 |
+
"grad_norm": 7.625,
|
| 18187 |
+
"learning_rate": 0.0004872973061072895,
|
| 18188 |
+
"loss": 17.3529,
|
| 18189 |
+
"step": 51940
|
| 18190 |
+
},
|
| 18191 |
+
{
|
| 18192 |
+
"epoch": 0.07696911162595026,
|
| 18193 |
+
"grad_norm": 7.40625,
|
| 18194 |
+
"learning_rate": 0.0004872923671722819,
|
| 18195 |
+
"loss": 17.3129,
|
| 18196 |
+
"step": 51960
|
| 18197 |
+
},
|
| 18198 |
+
{
|
| 18199 |
+
"epoch": 0.07699873791987866,
|
| 18200 |
+
"grad_norm": 7.0,
|
| 18201 |
+
"learning_rate": 0.00048728742823727435,
|
| 18202 |
+
"loss": 17.2937,
|
| 18203 |
+
"step": 51980
|
| 18204 |
+
},
|
| 18205 |
+
{
|
| 18206 |
+
"epoch": 0.07702836421380704,
|
| 18207 |
+
"grad_norm": 7.59375,
|
| 18208 |
+
"learning_rate": 0.00048728248930226674,
|
| 18209 |
+
"loss": 17.2637,
|
| 18210 |
+
"step": 52000
|
| 18211 |
}
|
| 18212 |
],
|
| 18213 |
"logging_steps": 20,
|
|
|
|
| 18227 |
"attributes": {}
|
| 18228 |
}
|
| 18229 |
},
|
| 18230 |
+
"total_flos": 3.822984044030093e+19,
|
| 18231 |
"train_batch_size": 48,
|
| 18232 |
"trial_name": null,
|
| 18233 |
"trial_params": null
|