Training in progress, step 84000, 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 sha256:4b0efb8be2586b96ebb4a5535f77f6a94fb348ad7e78bccfd805d4f163fc6d82
|
| 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 sha256:45b07b4d653abd4289bac11d275a8fa955c680796df31a5f7827a08967b8e980
|
| 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:f9d265cf6f50f9feb997539475c89f573fe4715116fd58e38d9aa82213e5b216
|
| 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 sha256:8da3be3a63442f65b9180ba61925236608ce8b82b7dea3c0e5f5d3608862bcef
|
| 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:fbedf96a0fb8d104fb9bad8615e16ce5894e29a2be6fb72446f5823ea3365ae6
|
| 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 sha256:9f81e35011a8c3a573c3479d39fc91d392677edf066ac64134db434dc646827f
|
| 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 sha256:384300172aace582cb6494e43de39b13911ea6caa46061bd078def72ec2ef51e
|
| 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,
|
|
@@ -29058,6 +29058,356 @@
|
|
| 29058 |
"learning_rate": 0.00047962714004053884,
|
| 29059 |
"loss": 16.2309,
|
| 29060 |
"step": 83000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29061 |
}
|
| 29062 |
],
|
| 29063 |
"logging_steps": 20,
|
|
@@ -29077,7 +29427,7 @@
|
|
| 29077 |
"attributes": {}
|
| 29078 |
}
|
| 29079 |
},
|
| 29080 |
-
"total_flos": 6.
|
| 29081 |
"train_batch_size": 48,
|
| 29082 |
"trial_name": null,
|
| 29083 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.12443043449922675,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 84000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 29058 |
"learning_rate": 0.00047962714004053884,
|
| 29059 |
"loss": 16.2309,
|
| 29060 |
"step": 83000
|
| 29061 |
+
},
|
| 29062 |
+
{
|
| 29063 |
+
"epoch": 0.12297874609673577,
|
| 29064 |
+
"grad_norm": 6.6875,
|
| 29065 |
+
"learning_rate": 0.00047962220110553123,
|
| 29066 |
+
"loss": 16.139,
|
| 29067 |
+
"step": 83020
|
| 29068 |
+
},
|
| 29069 |
+
{
|
| 29070 |
+
"epoch": 0.12300837239066416,
|
| 29071 |
+
"grad_norm": 7.03125,
|
| 29072 |
+
"learning_rate": 0.0004796172621705236,
|
| 29073 |
+
"loss": 16.2056,
|
| 29074 |
+
"step": 83040
|
| 29075 |
+
},
|
| 29076 |
+
{
|
| 29077 |
+
"epoch": 0.12303799868459254,
|
| 29078 |
+
"grad_norm": 6.4375,
|
| 29079 |
+
"learning_rate": 0.0004796123232355161,
|
| 29080 |
+
"loss": 16.202,
|
| 29081 |
+
"step": 83060
|
| 29082 |
+
},
|
| 29083 |
+
{
|
| 29084 |
+
"epoch": 0.12306762497852093,
|
| 29085 |
+
"grad_norm": 7.03125,
|
| 29086 |
+
"learning_rate": 0.0004796073843005085,
|
| 29087 |
+
"loss": 16.1796,
|
| 29088 |
+
"step": 83080
|
| 29089 |
+
},
|
| 29090 |
+
{
|
| 29091 |
+
"epoch": 0.12309725127244932,
|
| 29092 |
+
"grad_norm": 6.84375,
|
| 29093 |
+
"learning_rate": 0.00047960244536550097,
|
| 29094 |
+
"loss": 16.1404,
|
| 29095 |
+
"step": 83100
|
| 29096 |
+
},
|
| 29097 |
+
{
|
| 29098 |
+
"epoch": 0.12312687756637772,
|
| 29099 |
+
"grad_norm": 7.59375,
|
| 29100 |
+
"learning_rate": 0.00047959750643049336,
|
| 29101 |
+
"loss": 16.1799,
|
| 29102 |
+
"step": 83120
|
| 29103 |
+
},
|
| 29104 |
+
{
|
| 29105 |
+
"epoch": 0.1231565038603061,
|
| 29106 |
+
"grad_norm": 7.375,
|
| 29107 |
+
"learning_rate": 0.0004795925674954858,
|
| 29108 |
+
"loss": 16.1692,
|
| 29109 |
+
"step": 83140
|
| 29110 |
+
},
|
| 29111 |
+
{
|
| 29112 |
+
"epoch": 0.12318613015423449,
|
| 29113 |
+
"grad_norm": 7.15625,
|
| 29114 |
+
"learning_rate": 0.00047958762856047826,
|
| 29115 |
+
"loss": 16.1584,
|
| 29116 |
+
"step": 83160
|
| 29117 |
+
},
|
| 29118 |
+
{
|
| 29119 |
+
"epoch": 0.12321575644816288,
|
| 29120 |
+
"grad_norm": 6.34375,
|
| 29121 |
+
"learning_rate": 0.0004795826896254707,
|
| 29122 |
+
"loss": 16.2001,
|
| 29123 |
+
"step": 83180
|
| 29124 |
+
},
|
| 29125 |
+
{
|
| 29126 |
+
"epoch": 0.12324538274209126,
|
| 29127 |
+
"grad_norm": 7.34375,
|
| 29128 |
+
"learning_rate": 0.0004795777506904631,
|
| 29129 |
+
"loss": 16.2,
|
| 29130 |
+
"step": 83200
|
| 29131 |
+
},
|
| 29132 |
+
{
|
| 29133 |
+
"epoch": 0.12327500903601965,
|
| 29134 |
+
"grad_norm": 7.0625,
|
| 29135 |
+
"learning_rate": 0.0004795728117554556,
|
| 29136 |
+
"loss": 16.1916,
|
| 29137 |
+
"step": 83220
|
| 29138 |
+
},
|
| 29139 |
+
{
|
| 29140 |
+
"epoch": 0.12330463532994804,
|
| 29141 |
+
"grad_norm": 7.375,
|
| 29142 |
+
"learning_rate": 0.000479567872820448,
|
| 29143 |
+
"loss": 16.1917,
|
| 29144 |
+
"step": 83240
|
| 29145 |
+
},
|
| 29146 |
+
{
|
| 29147 |
+
"epoch": 0.12333426162387642,
|
| 29148 |
+
"grad_norm": 7.1875,
|
| 29149 |
+
"learning_rate": 0.00047956293388544044,
|
| 29150 |
+
"loss": 16.173,
|
| 29151 |
+
"step": 83260
|
| 29152 |
+
},
|
| 29153 |
+
{
|
| 29154 |
+
"epoch": 0.12336388791780481,
|
| 29155 |
+
"grad_norm": 6.96875,
|
| 29156 |
+
"learning_rate": 0.00047955799495043284,
|
| 29157 |
+
"loss": 16.1653,
|
| 29158 |
+
"step": 83280
|
| 29159 |
+
},
|
| 29160 |
+
{
|
| 29161 |
+
"epoch": 0.1233935142117332,
|
| 29162 |
+
"grad_norm": 8.5625,
|
| 29163 |
+
"learning_rate": 0.00047955305601542534,
|
| 29164 |
+
"loss": 16.215,
|
| 29165 |
+
"step": 83300
|
| 29166 |
+
},
|
| 29167 |
+
{
|
| 29168 |
+
"epoch": 0.12342314050566158,
|
| 29169 |
+
"grad_norm": 6.21875,
|
| 29170 |
+
"learning_rate": 0.00047954811708041773,
|
| 29171 |
+
"loss": 16.1763,
|
| 29172 |
+
"step": 83320
|
| 29173 |
+
},
|
| 29174 |
+
{
|
| 29175 |
+
"epoch": 0.12345276679958997,
|
| 29176 |
+
"grad_norm": 6.34375,
|
| 29177 |
+
"learning_rate": 0.0004795431781454102,
|
| 29178 |
+
"loss": 16.2133,
|
| 29179 |
+
"step": 83340
|
| 29180 |
+
},
|
| 29181 |
+
{
|
| 29182 |
+
"epoch": 0.12348239309351836,
|
| 29183 |
+
"grad_norm": 6.125,
|
| 29184 |
+
"learning_rate": 0.0004795382392104026,
|
| 29185 |
+
"loss": 16.1325,
|
| 29186 |
+
"step": 83360
|
| 29187 |
+
},
|
| 29188 |
+
{
|
| 29189 |
+
"epoch": 0.12351201938744674,
|
| 29190 |
+
"grad_norm": 6.8125,
|
| 29191 |
+
"learning_rate": 0.000479533300275395,
|
| 29192 |
+
"loss": 16.1738,
|
| 29193 |
+
"step": 83380
|
| 29194 |
+
},
|
| 29195 |
+
{
|
| 29196 |
+
"epoch": 0.12354164568137513,
|
| 29197 |
+
"grad_norm": 6.71875,
|
| 29198 |
+
"learning_rate": 0.00047952836134038747,
|
| 29199 |
+
"loss": 16.1694,
|
| 29200 |
+
"step": 83400
|
| 29201 |
+
},
|
| 29202 |
+
{
|
| 29203 |
+
"epoch": 0.12357127197530351,
|
| 29204 |
+
"grad_norm": 7.78125,
|
| 29205 |
+
"learning_rate": 0.00047952342240537986,
|
| 29206 |
+
"loss": 16.1704,
|
| 29207 |
+
"step": 83420
|
| 29208 |
+
},
|
| 29209 |
+
{
|
| 29210 |
+
"epoch": 0.12360089826923192,
|
| 29211 |
+
"grad_norm": 6.9375,
|
| 29212 |
+
"learning_rate": 0.0004795184834703723,
|
| 29213 |
+
"loss": 16.1661,
|
| 29214 |
+
"step": 83440
|
| 29215 |
+
},
|
| 29216 |
+
{
|
| 29217 |
+
"epoch": 0.1236305245631603,
|
| 29218 |
+
"grad_norm": 6.8125,
|
| 29219 |
+
"learning_rate": 0.00047951354453536476,
|
| 29220 |
+
"loss": 16.1131,
|
| 29221 |
+
"step": 83460
|
| 29222 |
+
},
|
| 29223 |
+
{
|
| 29224 |
+
"epoch": 0.12366015085708869,
|
| 29225 |
+
"grad_norm": 5.90625,
|
| 29226 |
+
"learning_rate": 0.0004795086056003572,
|
| 29227 |
+
"loss": 16.2239,
|
| 29228 |
+
"step": 83480
|
| 29229 |
+
},
|
| 29230 |
+
{
|
| 29231 |
+
"epoch": 0.12368977715101707,
|
| 29232 |
+
"grad_norm": 5.9375,
|
| 29233 |
+
"learning_rate": 0.0004795036666653496,
|
| 29234 |
+
"loss": 16.1863,
|
| 29235 |
+
"step": 83500
|
| 29236 |
+
},
|
| 29237 |
+
{
|
| 29238 |
+
"epoch": 0.12371940344494546,
|
| 29239 |
+
"grad_norm": 6.6875,
|
| 29240 |
+
"learning_rate": 0.0004794987277303421,
|
| 29241 |
+
"loss": 16.1254,
|
| 29242 |
+
"step": 83520
|
| 29243 |
+
},
|
| 29244 |
+
{
|
| 29245 |
+
"epoch": 0.12374902973887385,
|
| 29246 |
+
"grad_norm": 7.125,
|
| 29247 |
+
"learning_rate": 0.0004794937887953345,
|
| 29248 |
+
"loss": 16.2149,
|
| 29249 |
+
"step": 83540
|
| 29250 |
+
},
|
| 29251 |
+
{
|
| 29252 |
+
"epoch": 0.12377865603280223,
|
| 29253 |
+
"grad_norm": 7.21875,
|
| 29254 |
+
"learning_rate": 0.00047948884986032694,
|
| 29255 |
+
"loss": 16.1831,
|
| 29256 |
+
"step": 83560
|
| 29257 |
+
},
|
| 29258 |
+
{
|
| 29259 |
+
"epoch": 0.12380828232673062,
|
| 29260 |
+
"grad_norm": 6.40625,
|
| 29261 |
+
"learning_rate": 0.00047948391092531934,
|
| 29262 |
+
"loss": 16.1633,
|
| 29263 |
+
"step": 83580
|
| 29264 |
+
},
|
| 29265 |
+
{
|
| 29266 |
+
"epoch": 0.123837908620659,
|
| 29267 |
+
"grad_norm": 7.5,
|
| 29268 |
+
"learning_rate": 0.00047947897199031184,
|
| 29269 |
+
"loss": 16.1849,
|
| 29270 |
+
"step": 83600
|
| 29271 |
+
},
|
| 29272 |
+
{
|
| 29273 |
+
"epoch": 0.1238675349145874,
|
| 29274 |
+
"grad_norm": 7.09375,
|
| 29275 |
+
"learning_rate": 0.00047947403305530423,
|
| 29276 |
+
"loss": 16.1654,
|
| 29277 |
+
"step": 83620
|
| 29278 |
+
},
|
| 29279 |
+
{
|
| 29280 |
+
"epoch": 0.12389716120851578,
|
| 29281 |
+
"grad_norm": 6.84375,
|
| 29282 |
+
"learning_rate": 0.0004794690941202967,
|
| 29283 |
+
"loss": 16.2204,
|
| 29284 |
+
"step": 83640
|
| 29285 |
+
},
|
| 29286 |
+
{
|
| 29287 |
+
"epoch": 0.12392678750244417,
|
| 29288 |
+
"grad_norm": 6.34375,
|
| 29289 |
+
"learning_rate": 0.0004794641551852891,
|
| 29290 |
+
"loss": 16.1609,
|
| 29291 |
+
"step": 83660
|
| 29292 |
+
},
|
| 29293 |
+
{
|
| 29294 |
+
"epoch": 0.12395641379637255,
|
| 29295 |
+
"grad_norm": 6.0,
|
| 29296 |
+
"learning_rate": 0.0004794592162502816,
|
| 29297 |
+
"loss": 16.1497,
|
| 29298 |
+
"step": 83680
|
| 29299 |
+
},
|
| 29300 |
+
{
|
| 29301 |
+
"epoch": 0.12398604009030094,
|
| 29302 |
+
"grad_norm": 7.09375,
|
| 29303 |
+
"learning_rate": 0.00047945427731527397,
|
| 29304 |
+
"loss": 16.2024,
|
| 29305 |
+
"step": 83700
|
| 29306 |
+
},
|
| 29307 |
+
{
|
| 29308 |
+
"epoch": 0.12401566638422933,
|
| 29309 |
+
"grad_norm": 7.3125,
|
| 29310 |
+
"learning_rate": 0.00047944933838026636,
|
| 29311 |
+
"loss": 16.2298,
|
| 29312 |
+
"step": 83720
|
| 29313 |
+
},
|
| 29314 |
+
{
|
| 29315 |
+
"epoch": 0.12404529267815771,
|
| 29316 |
+
"grad_norm": 7.625,
|
| 29317 |
+
"learning_rate": 0.0004794443994452588,
|
| 29318 |
+
"loss": 16.1594,
|
| 29319 |
+
"step": 83740
|
| 29320 |
+
},
|
| 29321 |
+
{
|
| 29322 |
+
"epoch": 0.12407491897208611,
|
| 29323 |
+
"grad_norm": 6.40625,
|
| 29324 |
+
"learning_rate": 0.00047943946051025126,
|
| 29325 |
+
"loss": 16.138,
|
| 29326 |
+
"step": 83760
|
| 29327 |
+
},
|
| 29328 |
+
{
|
| 29329 |
+
"epoch": 0.1241045452660145,
|
| 29330 |
+
"grad_norm": 7.625,
|
| 29331 |
+
"learning_rate": 0.0004794345215752437,
|
| 29332 |
+
"loss": 16.1493,
|
| 29333 |
+
"step": 83780
|
| 29334 |
+
},
|
| 29335 |
+
{
|
| 29336 |
+
"epoch": 0.12413417155994289,
|
| 29337 |
+
"grad_norm": 7.34375,
|
| 29338 |
+
"learning_rate": 0.0004794295826402361,
|
| 29339 |
+
"loss": 16.1952,
|
| 29340 |
+
"step": 83800
|
| 29341 |
+
},
|
| 29342 |
+
{
|
| 29343 |
+
"epoch": 0.12416379785387127,
|
| 29344 |
+
"grad_norm": 6.5625,
|
| 29345 |
+
"learning_rate": 0.0004794246437052286,
|
| 29346 |
+
"loss": 16.1847,
|
| 29347 |
+
"step": 83820
|
| 29348 |
+
},
|
| 29349 |
+
{
|
| 29350 |
+
"epoch": 0.12419342414779966,
|
| 29351 |
+
"grad_norm": 6.34375,
|
| 29352 |
+
"learning_rate": 0.000479419704770221,
|
| 29353 |
+
"loss": 16.2249,
|
| 29354 |
+
"step": 83840
|
| 29355 |
+
},
|
| 29356 |
+
{
|
| 29357 |
+
"epoch": 0.12422305044172804,
|
| 29358 |
+
"grad_norm": 6.15625,
|
| 29359 |
+
"learning_rate": 0.00047941476583521344,
|
| 29360 |
+
"loss": 16.1628,
|
| 29361 |
+
"step": 83860
|
| 29362 |
+
},
|
| 29363 |
+
{
|
| 29364 |
+
"epoch": 0.12425267673565643,
|
| 29365 |
+
"grad_norm": 6.3125,
|
| 29366 |
+
"learning_rate": 0.00047940982690020584,
|
| 29367 |
+
"loss": 16.1391,
|
| 29368 |
+
"step": 83880
|
| 29369 |
+
},
|
| 29370 |
+
{
|
| 29371 |
+
"epoch": 0.12428230302958482,
|
| 29372 |
+
"grad_norm": 6.21875,
|
| 29373 |
+
"learning_rate": 0.00047940488796519834,
|
| 29374 |
+
"loss": 16.1901,
|
| 29375 |
+
"step": 83900
|
| 29376 |
+
},
|
| 29377 |
+
{
|
| 29378 |
+
"epoch": 0.1243119293235132,
|
| 29379 |
+
"grad_norm": 6.84375,
|
| 29380 |
+
"learning_rate": 0.00047939994903019073,
|
| 29381 |
+
"loss": 16.136,
|
| 29382 |
+
"step": 83920
|
| 29383 |
+
},
|
| 29384 |
+
{
|
| 29385 |
+
"epoch": 0.12434155561744159,
|
| 29386 |
+
"grad_norm": 6.84375,
|
| 29387 |
+
"learning_rate": 0.0004793950100951832,
|
| 29388 |
+
"loss": 16.1843,
|
| 29389 |
+
"step": 83940
|
| 29390 |
+
},
|
| 29391 |
+
{
|
| 29392 |
+
"epoch": 0.12437118191136998,
|
| 29393 |
+
"grad_norm": 6.40625,
|
| 29394 |
+
"learning_rate": 0.0004793900711601756,
|
| 29395 |
+
"loss": 16.1407,
|
| 29396 |
+
"step": 83960
|
| 29397 |
+
},
|
| 29398 |
+
{
|
| 29399 |
+
"epoch": 0.12440080820529836,
|
| 29400 |
+
"grad_norm": 7.59375,
|
| 29401 |
+
"learning_rate": 0.0004793851322251681,
|
| 29402 |
+
"loss": 16.1422,
|
| 29403 |
+
"step": 83980
|
| 29404 |
+
},
|
| 29405 |
+
{
|
| 29406 |
+
"epoch": 0.12443043449922675,
|
| 29407 |
+
"grad_norm": 6.625,
|
| 29408 |
+
"learning_rate": 0.00047938019329016047,
|
| 29409 |
+
"loss": 16.1804,
|
| 29410 |
+
"step": 84000
|
| 29411 |
}
|
| 29412 |
],
|
| 29413 |
"logging_steps": 20,
|
|
|
|
| 29427 |
"attributes": {}
|
| 29428 |
}
|
| 29429 |
},
|
| 29430 |
+
"total_flos": 6.176144902183715e+19,
|
| 29431 |
"train_batch_size": 48,
|
| 29432 |
"trial_name": null,
|
| 29433 |
"trial_params": null
|