Training in progress, step 64000, 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 sha256:7e9e2e28af6146afe43cdb907b3f739f4250419722a504936d499d748c4273c2
|
| 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:c525619271d9f1b159f2a02689faf274b91a24f4060671d1bb043b475555d14b
|
| 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:c8fe2fa95e31f3dc937f9b59092c7fb6de9e0372df41bd2a550664b6f79e7cbe
|
| 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:ddd0689c77fb3ffbdf3d22ae0befd6523eb49cce62bb898a2d1d04c2e59b3de2
|
| 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:b437d66c3e323d9fae406e3bdd63ddc02e9d57b750cf3643ed3c31e499dbfb12
|
| 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:c70d134be552c48d75f5da0fead9e7f38ab9249126492a9649cbf91ed80be65e
|
| 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:d97a57bb76da837e81db32d9310adda34d8e8142bafc95b7825ffc93afda92db
|
| 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,
|
|
@@ -22058,6 +22058,356 @@
|
|
| 22058 |
"learning_rate": 0.00048456607504810523,
|
| 22059 |
"loss": 16.7568,
|
| 22060 |
"step": 63000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22061 |
}
|
| 22062 |
],
|
| 22063 |
"logging_steps": 20,
|
|
@@ -22077,7 +22427,7 @@
|
|
| 22077 |
"attributes": {}
|
| 22078 |
}
|
| 22079 |
},
|
| 22080 |
-
"total_flos": 4.
|
| 22081 |
"train_batch_size": 48,
|
| 22082 |
"trial_name": null,
|
| 22083 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.09480414057083943,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 64000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 22058 |
"learning_rate": 0.00048456607504810523,
|
| 22059 |
"loss": 16.7568,
|
| 22060 |
"step": 63000
|
| 22061 |
+
},
|
| 22062 |
+
{
|
| 22063 |
+
"epoch": 0.09335245216834845,
|
| 22064 |
+
"grad_norm": 6.9375,
|
| 22065 |
+
"learning_rate": 0.0004845611361130977,
|
| 22066 |
+
"loss": 16.8394,
|
| 22067 |
+
"step": 63020
|
| 22068 |
+
},
|
| 22069 |
+
{
|
| 22070 |
+
"epoch": 0.09338207846227684,
|
| 22071 |
+
"grad_norm": 6.53125,
|
| 22072 |
+
"learning_rate": 0.0004845561971780901,
|
| 22073 |
+
"loss": 16.8243,
|
| 22074 |
+
"step": 63040
|
| 22075 |
+
},
|
| 22076 |
+
{
|
| 22077 |
+
"epoch": 0.09341170475620522,
|
| 22078 |
+
"grad_norm": 6.9375,
|
| 22079 |
+
"learning_rate": 0.0004845512582430826,
|
| 22080 |
+
"loss": 16.7747,
|
| 22081 |
+
"step": 63060
|
| 22082 |
+
},
|
| 22083 |
+
{
|
| 22084 |
+
"epoch": 0.09344133105013361,
|
| 22085 |
+
"grad_norm": 7.65625,
|
| 22086 |
+
"learning_rate": 0.00048454631930807497,
|
| 22087 |
+
"loss": 16.7301,
|
| 22088 |
+
"step": 63080
|
| 22089 |
+
},
|
| 22090 |
+
{
|
| 22091 |
+
"epoch": 0.09347095734406201,
|
| 22092 |
+
"grad_norm": 6.875,
|
| 22093 |
+
"learning_rate": 0.00048454138037306736,
|
| 22094 |
+
"loss": 16.7784,
|
| 22095 |
+
"step": 63100
|
| 22096 |
+
},
|
| 22097 |
+
{
|
| 22098 |
+
"epoch": 0.0935005836379904,
|
| 22099 |
+
"grad_norm": 7.46875,
|
| 22100 |
+
"learning_rate": 0.00048453644143805986,
|
| 22101 |
+
"loss": 16.7329,
|
| 22102 |
+
"step": 63120
|
| 22103 |
+
},
|
| 22104 |
+
{
|
| 22105 |
+
"epoch": 0.09353020993191878,
|
| 22106 |
+
"grad_norm": 6.65625,
|
| 22107 |
+
"learning_rate": 0.00048453150250305226,
|
| 22108 |
+
"loss": 16.7494,
|
| 22109 |
+
"step": 63140
|
| 22110 |
+
},
|
| 22111 |
+
{
|
| 22112 |
+
"epoch": 0.09355983622584717,
|
| 22113 |
+
"grad_norm": 7.0625,
|
| 22114 |
+
"learning_rate": 0.0004845265635680447,
|
| 22115 |
+
"loss": 16.7277,
|
| 22116 |
+
"step": 63160
|
| 22117 |
+
},
|
| 22118 |
+
{
|
| 22119 |
+
"epoch": 0.09358946251977555,
|
| 22120 |
+
"grad_norm": 6.90625,
|
| 22121 |
+
"learning_rate": 0.0004845216246330371,
|
| 22122 |
+
"loss": 16.723,
|
| 22123 |
+
"step": 63180
|
| 22124 |
+
},
|
| 22125 |
+
{
|
| 22126 |
+
"epoch": 0.09361908881370394,
|
| 22127 |
+
"grad_norm": 6.40625,
|
| 22128 |
+
"learning_rate": 0.0004845166856980296,
|
| 22129 |
+
"loss": 16.7447,
|
| 22130 |
+
"step": 63200
|
| 22131 |
+
},
|
| 22132 |
+
{
|
| 22133 |
+
"epoch": 0.09364871510763233,
|
| 22134 |
+
"grad_norm": 5.8125,
|
| 22135 |
+
"learning_rate": 0.000484511746763022,
|
| 22136 |
+
"loss": 16.7586,
|
| 22137 |
+
"step": 63220
|
| 22138 |
+
},
|
| 22139 |
+
{
|
| 22140 |
+
"epoch": 0.09367834140156071,
|
| 22141 |
+
"grad_norm": 6.125,
|
| 22142 |
+
"learning_rate": 0.00048450680782801444,
|
| 22143 |
+
"loss": 16.7316,
|
| 22144 |
+
"step": 63240
|
| 22145 |
+
},
|
| 22146 |
+
{
|
| 22147 |
+
"epoch": 0.0937079676954891,
|
| 22148 |
+
"grad_norm": 6.125,
|
| 22149 |
+
"learning_rate": 0.00048450186889300684,
|
| 22150 |
+
"loss": 16.6967,
|
| 22151 |
+
"step": 63260
|
| 22152 |
+
},
|
| 22153 |
+
{
|
| 22154 |
+
"epoch": 0.09373759398941749,
|
| 22155 |
+
"grad_norm": 6.53125,
|
| 22156 |
+
"learning_rate": 0.00048449692995799934,
|
| 22157 |
+
"loss": 16.7287,
|
| 22158 |
+
"step": 63280
|
| 22159 |
+
},
|
| 22160 |
+
{
|
| 22161 |
+
"epoch": 0.09376722028334587,
|
| 22162 |
+
"grad_norm": 6.53125,
|
| 22163 |
+
"learning_rate": 0.00048449199102299173,
|
| 22164 |
+
"loss": 16.78,
|
| 22165 |
+
"step": 63300
|
| 22166 |
+
},
|
| 22167 |
+
{
|
| 22168 |
+
"epoch": 0.09379684657727426,
|
| 22169 |
+
"grad_norm": 6.625,
|
| 22170 |
+
"learning_rate": 0.0004844870520879842,
|
| 22171 |
+
"loss": 16.7051,
|
| 22172 |
+
"step": 63320
|
| 22173 |
+
},
|
| 22174 |
+
{
|
| 22175 |
+
"epoch": 0.09382647287120265,
|
| 22176 |
+
"grad_norm": 7.28125,
|
| 22177 |
+
"learning_rate": 0.0004844821131529766,
|
| 22178 |
+
"loss": 16.7584,
|
| 22179 |
+
"step": 63340
|
| 22180 |
+
},
|
| 22181 |
+
{
|
| 22182 |
+
"epoch": 0.09385609916513103,
|
| 22183 |
+
"grad_norm": 7.84375,
|
| 22184 |
+
"learning_rate": 0.0004844771742179691,
|
| 22185 |
+
"loss": 16.7307,
|
| 22186 |
+
"step": 63360
|
| 22187 |
+
},
|
| 22188 |
+
{
|
| 22189 |
+
"epoch": 0.09388572545905942,
|
| 22190 |
+
"grad_norm": 6.78125,
|
| 22191 |
+
"learning_rate": 0.00048447223528296147,
|
| 22192 |
+
"loss": 16.7168,
|
| 22193 |
+
"step": 63380
|
| 22194 |
+
},
|
| 22195 |
+
{
|
| 22196 |
+
"epoch": 0.0939153517529878,
|
| 22197 |
+
"grad_norm": 6.53125,
|
| 22198 |
+
"learning_rate": 0.0004844672963479539,
|
| 22199 |
+
"loss": 16.6948,
|
| 22200 |
+
"step": 63400
|
| 22201 |
+
},
|
| 22202 |
+
{
|
| 22203 |
+
"epoch": 0.0939449780469162,
|
| 22204 |
+
"grad_norm": 6.59375,
|
| 22205 |
+
"learning_rate": 0.00048446235741294636,
|
| 22206 |
+
"loss": 16.7118,
|
| 22207 |
+
"step": 63420
|
| 22208 |
+
},
|
| 22209 |
+
{
|
| 22210 |
+
"epoch": 0.09397460434084459,
|
| 22211 |
+
"grad_norm": 6.90625,
|
| 22212 |
+
"learning_rate": 0.00048445741847793876,
|
| 22213 |
+
"loss": 16.7566,
|
| 22214 |
+
"step": 63440
|
| 22215 |
+
},
|
| 22216 |
+
{
|
| 22217 |
+
"epoch": 0.09400423063477298,
|
| 22218 |
+
"grad_norm": 6.53125,
|
| 22219 |
+
"learning_rate": 0.0004844524795429312,
|
| 22220 |
+
"loss": 16.7323,
|
| 22221 |
+
"step": 63460
|
| 22222 |
+
},
|
| 22223 |
+
{
|
| 22224 |
+
"epoch": 0.09403385692870136,
|
| 22225 |
+
"grad_norm": 6.46875,
|
| 22226 |
+
"learning_rate": 0.0004844475406079236,
|
| 22227 |
+
"loss": 16.7964,
|
| 22228 |
+
"step": 63480
|
| 22229 |
+
},
|
| 22230 |
+
{
|
| 22231 |
+
"epoch": 0.09406348322262975,
|
| 22232 |
+
"grad_norm": 6.65625,
|
| 22233 |
+
"learning_rate": 0.0004844426016729161,
|
| 22234 |
+
"loss": 16.7028,
|
| 22235 |
+
"step": 63500
|
| 22236 |
+
},
|
| 22237 |
+
{
|
| 22238 |
+
"epoch": 0.09409310951655814,
|
| 22239 |
+
"grad_norm": 6.84375,
|
| 22240 |
+
"learning_rate": 0.0004844376627379085,
|
| 22241 |
+
"loss": 16.7663,
|
| 22242 |
+
"step": 63520
|
| 22243 |
+
},
|
| 22244 |
+
{
|
| 22245 |
+
"epoch": 0.09412273581048652,
|
| 22246 |
+
"grad_norm": 7.09375,
|
| 22247 |
+
"learning_rate": 0.00048443272380290094,
|
| 22248 |
+
"loss": 16.7777,
|
| 22249 |
+
"step": 63540
|
| 22250 |
+
},
|
| 22251 |
+
{
|
| 22252 |
+
"epoch": 0.09415236210441491,
|
| 22253 |
+
"grad_norm": 7.28125,
|
| 22254 |
+
"learning_rate": 0.00048442778486789334,
|
| 22255 |
+
"loss": 16.7348,
|
| 22256 |
+
"step": 63560
|
| 22257 |
+
},
|
| 22258 |
+
{
|
| 22259 |
+
"epoch": 0.0941819883983433,
|
| 22260 |
+
"grad_norm": 6.5,
|
| 22261 |
+
"learning_rate": 0.00048442284593288584,
|
| 22262 |
+
"loss": 16.7293,
|
| 22263 |
+
"step": 63580
|
| 22264 |
+
},
|
| 22265 |
+
{
|
| 22266 |
+
"epoch": 0.09421161469227168,
|
| 22267 |
+
"grad_norm": 6.28125,
|
| 22268 |
+
"learning_rate": 0.00048441790699787823,
|
| 22269 |
+
"loss": 16.7371,
|
| 22270 |
+
"step": 63600
|
| 22271 |
+
},
|
| 22272 |
+
{
|
| 22273 |
+
"epoch": 0.09424124098620007,
|
| 22274 |
+
"grad_norm": 6.84375,
|
| 22275 |
+
"learning_rate": 0.0004844129680628707,
|
| 22276 |
+
"loss": 16.7628,
|
| 22277 |
+
"step": 63620
|
| 22278 |
+
},
|
| 22279 |
+
{
|
| 22280 |
+
"epoch": 0.09427086728012846,
|
| 22281 |
+
"grad_norm": 6.9375,
|
| 22282 |
+
"learning_rate": 0.00048440802912786313,
|
| 22283 |
+
"loss": 16.743,
|
| 22284 |
+
"step": 63640
|
| 22285 |
+
},
|
| 22286 |
+
{
|
| 22287 |
+
"epoch": 0.09430049357405684,
|
| 22288 |
+
"grad_norm": 6.46875,
|
| 22289 |
+
"learning_rate": 0.0004844030901928556,
|
| 22290 |
+
"loss": 16.759,
|
| 22291 |
+
"step": 63660
|
| 22292 |
+
},
|
| 22293 |
+
{
|
| 22294 |
+
"epoch": 0.09433011986798523,
|
| 22295 |
+
"grad_norm": 6.78125,
|
| 22296 |
+
"learning_rate": 0.00048439815125784797,
|
| 22297 |
+
"loss": 16.781,
|
| 22298 |
+
"step": 63680
|
| 22299 |
+
},
|
| 22300 |
+
{
|
| 22301 |
+
"epoch": 0.09435974616191362,
|
| 22302 |
+
"grad_norm": 6.28125,
|
| 22303 |
+
"learning_rate": 0.0004843932123228404,
|
| 22304 |
+
"loss": 16.7374,
|
| 22305 |
+
"step": 63700
|
| 22306 |
+
},
|
| 22307 |
+
{
|
| 22308 |
+
"epoch": 0.094389372455842,
|
| 22309 |
+
"grad_norm": 7.125,
|
| 22310 |
+
"learning_rate": 0.00048438827338783286,
|
| 22311 |
+
"loss": 16.767,
|
| 22312 |
+
"step": 63720
|
| 22313 |
+
},
|
| 22314 |
+
{
|
| 22315 |
+
"epoch": 0.0944189987497704,
|
| 22316 |
+
"grad_norm": 7.34375,
|
| 22317 |
+
"learning_rate": 0.0004843833344528253,
|
| 22318 |
+
"loss": 16.6797,
|
| 22319 |
+
"step": 63740
|
| 22320 |
+
},
|
| 22321 |
+
{
|
| 22322 |
+
"epoch": 0.09444862504369879,
|
| 22323 |
+
"grad_norm": 7.15625,
|
| 22324 |
+
"learning_rate": 0.0004843783955178177,
|
| 22325 |
+
"loss": 16.7178,
|
| 22326 |
+
"step": 63760
|
| 22327 |
+
},
|
| 22328 |
+
{
|
| 22329 |
+
"epoch": 0.09447825133762718,
|
| 22330 |
+
"grad_norm": 7.03125,
|
| 22331 |
+
"learning_rate": 0.0004843734565828101,
|
| 22332 |
+
"loss": 16.7747,
|
| 22333 |
+
"step": 63780
|
| 22334 |
+
},
|
| 22335 |
+
{
|
| 22336 |
+
"epoch": 0.09450787763155556,
|
| 22337 |
+
"grad_norm": 6.15625,
|
| 22338 |
+
"learning_rate": 0.0004843685176478026,
|
| 22339 |
+
"loss": 16.722,
|
| 22340 |
+
"step": 63800
|
| 22341 |
+
},
|
| 22342 |
+
{
|
| 22343 |
+
"epoch": 0.09453750392548395,
|
| 22344 |
+
"grad_norm": 6.46875,
|
| 22345 |
+
"learning_rate": 0.000484363578712795,
|
| 22346 |
+
"loss": 16.7015,
|
| 22347 |
+
"step": 63820
|
| 22348 |
+
},
|
| 22349 |
+
{
|
| 22350 |
+
"epoch": 0.09456713021941233,
|
| 22351 |
+
"grad_norm": 9.25,
|
| 22352 |
+
"learning_rate": 0.00048435863977778744,
|
| 22353 |
+
"loss": 16.7375,
|
| 22354 |
+
"step": 63840
|
| 22355 |
+
},
|
| 22356 |
+
{
|
| 22357 |
+
"epoch": 0.09459675651334072,
|
| 22358 |
+
"grad_norm": 6.90625,
|
| 22359 |
+
"learning_rate": 0.00048435370084277984,
|
| 22360 |
+
"loss": 16.7442,
|
| 22361 |
+
"step": 63860
|
| 22362 |
+
},
|
| 22363 |
+
{
|
| 22364 |
+
"epoch": 0.09462638280726911,
|
| 22365 |
+
"grad_norm": 6.78125,
|
| 22366 |
+
"learning_rate": 0.00048434876190777234,
|
| 22367 |
+
"loss": 16.7361,
|
| 22368 |
+
"step": 63880
|
| 22369 |
+
},
|
| 22370 |
+
{
|
| 22371 |
+
"epoch": 0.0946560091011975,
|
| 22372 |
+
"grad_norm": 6.46875,
|
| 22373 |
+
"learning_rate": 0.00048434382297276473,
|
| 22374 |
+
"loss": 16.7216,
|
| 22375 |
+
"step": 63900
|
| 22376 |
+
},
|
| 22377 |
+
{
|
| 22378 |
+
"epoch": 0.09468563539512588,
|
| 22379 |
+
"grad_norm": 6.84375,
|
| 22380 |
+
"learning_rate": 0.0004843388840377572,
|
| 22381 |
+
"loss": 16.7706,
|
| 22382 |
+
"step": 63920
|
| 22383 |
+
},
|
| 22384 |
+
{
|
| 22385 |
+
"epoch": 0.09471526168905427,
|
| 22386 |
+
"grad_norm": 6.6875,
|
| 22387 |
+
"learning_rate": 0.00048433394510274963,
|
| 22388 |
+
"loss": 16.6918,
|
| 22389 |
+
"step": 63940
|
| 22390 |
+
},
|
| 22391 |
+
{
|
| 22392 |
+
"epoch": 0.09474488798298265,
|
| 22393 |
+
"grad_norm": 6.78125,
|
| 22394 |
+
"learning_rate": 0.0004843290061677421,
|
| 22395 |
+
"loss": 16.6463,
|
| 22396 |
+
"step": 63960
|
| 22397 |
+
},
|
| 22398 |
+
{
|
| 22399 |
+
"epoch": 0.09477451427691104,
|
| 22400 |
+
"grad_norm": 7.21875,
|
| 22401 |
+
"learning_rate": 0.00048432406723273447,
|
| 22402 |
+
"loss": 16.7036,
|
| 22403 |
+
"step": 63980
|
| 22404 |
+
},
|
| 22405 |
+
{
|
| 22406 |
+
"epoch": 0.09480414057083943,
|
| 22407 |
+
"grad_norm": 6.09375,
|
| 22408 |
+
"learning_rate": 0.0004843191282977269,
|
| 22409 |
+
"loss": 16.7843,
|
| 22410 |
+
"step": 64000
|
| 22411 |
}
|
| 22412 |
],
|
| 22413 |
"logging_steps": 20,
|
|
|
|
| 22427 |
"attributes": {}
|
| 22428 |
}
|
| 22429 |
},
|
| 22430 |
+
"total_flos": 4.705415858527142e+19,
|
| 22431 |
"train_batch_size": 48,
|
| 22432 |
"trial_name": null,
|
| 22433 |
"trial_params": null
|