Training in progress, step 56000, 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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbc019d20c5bc5141a3e9004bef5a52531dc2a92512d93ad8455f732db0eb48d
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd70cbbec6d1891a81fb67c9296a4bf20c7702703681faa48b7e22206072facc
|
| 3 |
size 938825803
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fcedeb5e64ebf070876b0c1c4c22aebd04ef9acb651910f4b487df10455e11d
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46e948248514973c2ef1b72e4ce8dd6fba8939559c40be1ef19c251df415a7e3
|
| 3 |
size 1465
|
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": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -4064,6 +4064,318 @@
|
|
| 4064 |
"eval_samples_per_second": 77.409,
|
| 4065 |
"eval_steps_per_second": 19.352,
|
| 4066 |
"step": 52000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4067 |
}
|
| 4068 |
],
|
| 4069 |
"logging_steps": 100,
|
|
@@ -4083,7 +4395,7 @@
|
|
| 4083 |
"attributes": {}
|
| 4084 |
}
|
| 4085 |
},
|
| 4086 |
-
"total_flos": 1.
|
| 4087 |
"train_batch_size": 22,
|
| 4088 |
"trial_name": null,
|
| 4089 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.18181818181818182,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 56000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4064 |
"eval_samples_per_second": 77.409,
|
| 4065 |
"eval_steps_per_second": 19.352,
|
| 4066 |
"step": 52000
|
| 4067 |
+
},
|
| 4068 |
+
{
|
| 4069 |
+
"epoch": 0.14636363636363636,
|
| 4070 |
+
"grad_norm": 0.15897710621356964,
|
| 4071 |
+
"learning_rate": 0.0005425038522701411,
|
| 4072 |
+
"loss": 2.6896728515625,
|
| 4073 |
+
"step": 52100
|
| 4074 |
+
},
|
| 4075 |
+
{
|
| 4076 |
+
"epoch": 0.14727272727272728,
|
| 4077 |
+
"grad_norm": 0.1507830172777176,
|
| 4078 |
+
"learning_rate": 0.0005410789097916161,
|
| 4079 |
+
"loss": 2.661712341308594,
|
| 4080 |
+
"step": 52200
|
| 4081 |
+
},
|
| 4082 |
+
{
|
| 4083 |
+
"epoch": 0.1481818181818182,
|
| 4084 |
+
"grad_norm": 0.1556272655725479,
|
| 4085 |
+
"learning_rate": 0.0005396536313293696,
|
| 4086 |
+
"loss": 2.6831851196289063,
|
| 4087 |
+
"step": 52300
|
| 4088 |
+
},
|
| 4089 |
+
{
|
| 4090 |
+
"epoch": 0.14909090909090908,
|
| 4091 |
+
"grad_norm": 0.15099219977855682,
|
| 4092 |
+
"learning_rate": 0.0005382280285407307,
|
| 4093 |
+
"loss": 2.6684881591796876,
|
| 4094 |
+
"step": 52400
|
| 4095 |
+
},
|
| 4096 |
+
{
|
| 4097 |
+
"epoch": 0.15,
|
| 4098 |
+
"grad_norm": 0.15491120517253876,
|
| 4099 |
+
"learning_rate": 0.0005368021130856809,
|
| 4100 |
+
"loss": 2.673580322265625,
|
| 4101 |
+
"step": 52500
|
| 4102 |
+
},
|
| 4103 |
+
{
|
| 4104 |
+
"epoch": 0.1509090909090909,
|
| 4105 |
+
"grad_norm": 0.1487579345703125,
|
| 4106 |
+
"learning_rate": 0.0005353758966267588,
|
| 4107 |
+
"loss": 2.690845642089844,
|
| 4108 |
+
"step": 52600
|
| 4109 |
+
},
|
| 4110 |
+
{
|
| 4111 |
+
"epoch": 0.15181818181818182,
|
| 4112 |
+
"grad_norm": 0.1554812639951706,
|
| 4113 |
+
"learning_rate": 0.0005339493908289656,
|
| 4114 |
+
"loss": 2.67916748046875,
|
| 4115 |
+
"step": 52700
|
| 4116 |
+
},
|
| 4117 |
+
{
|
| 4118 |
+
"epoch": 0.15272727272727274,
|
| 4119 |
+
"grad_norm": 0.15371479094028473,
|
| 4120 |
+
"learning_rate": 0.0005325226073596681,
|
| 4121 |
+
"loss": 2.6689898681640627,
|
| 4122 |
+
"step": 52800
|
| 4123 |
+
},
|
| 4124 |
+
{
|
| 4125 |
+
"epoch": 0.15363636363636363,
|
| 4126 |
+
"grad_norm": 0.21308736503124237,
|
| 4127 |
+
"learning_rate": 0.0005310955578885049,
|
| 4128 |
+
"loss": 2.696147766113281,
|
| 4129 |
+
"step": 52900
|
| 4130 |
+
},
|
| 4131 |
+
{
|
| 4132 |
+
"epoch": 0.15454545454545454,
|
| 4133 |
+
"grad_norm": 0.15344563126564026,
|
| 4134 |
+
"learning_rate": 0.0005296682540872898,
|
| 4135 |
+
"loss": 2.6800167846679686,
|
| 4136 |
+
"step": 53000
|
| 4137 |
+
},
|
| 4138 |
+
{
|
| 4139 |
+
"epoch": 0.15454545454545454,
|
| 4140 |
+
"eval_loss": 3.073288917541504,
|
| 4141 |
+
"eval_runtime": 7.4514,
|
| 4142 |
+
"eval_samples_per_second": 77.301,
|
| 4143 |
+
"eval_steps_per_second": 19.325,
|
| 4144 |
+
"step": 53000
|
| 4145 |
+
},
|
| 4146 |
+
{
|
| 4147 |
+
"epoch": 0.15545454545454546,
|
| 4148 |
+
"grad_norm": 0.14833194017410278,
|
| 4149 |
+
"learning_rate": 0.000528240707629917,
|
| 4150 |
+
"loss": 2.6591696166992187,
|
| 4151 |
+
"step": 53100
|
| 4152 |
+
},
|
| 4153 |
+
{
|
| 4154 |
+
"epoch": 0.15636363636363637,
|
| 4155 |
+
"grad_norm": 0.200588196516037,
|
| 4156 |
+
"learning_rate": 0.0005268129301922651,
|
| 4157 |
+
"loss": 2.652269287109375,
|
| 4158 |
+
"step": 53200
|
| 4159 |
+
},
|
| 4160 |
+
{
|
| 4161 |
+
"epoch": 0.1572727272727273,
|
| 4162 |
+
"grad_norm": 0.1412370204925537,
|
| 4163 |
+
"learning_rate": 0.0005253849334521023,
|
| 4164 |
+
"loss": 2.674943542480469,
|
| 4165 |
+
"step": 53300
|
| 4166 |
+
},
|
| 4167 |
+
{
|
| 4168 |
+
"epoch": 0.15818181818181817,
|
| 4169 |
+
"grad_norm": 0.1481807678937912,
|
| 4170 |
+
"learning_rate": 0.0005239567290889901,
|
| 4171 |
+
"loss": 2.6497378540039063,
|
| 4172 |
+
"step": 53400
|
| 4173 |
+
},
|
| 4174 |
+
{
|
| 4175 |
+
"epoch": 0.1590909090909091,
|
| 4176 |
+
"grad_norm": 0.1553225964307785,
|
| 4177 |
+
"learning_rate": 0.0005225283287841883,
|
| 4178 |
+
"loss": 2.655411682128906,
|
| 4179 |
+
"step": 53500
|
| 4180 |
+
},
|
| 4181 |
+
{
|
| 4182 |
+
"epoch": 0.16,
|
| 4183 |
+
"grad_norm": 0.1549694985151291,
|
| 4184 |
+
"learning_rate": 0.0005210997442205594,
|
| 4185 |
+
"loss": 2.654962158203125,
|
| 4186 |
+
"step": 53600
|
| 4187 |
+
},
|
| 4188 |
+
{
|
| 4189 |
+
"epoch": 0.16090909090909092,
|
| 4190 |
+
"grad_norm": 0.1860799938440323,
|
| 4191 |
+
"learning_rate": 0.0005196709870824726,
|
| 4192 |
+
"loss": 2.6886834716796875,
|
| 4193 |
+
"step": 53700
|
| 4194 |
+
},
|
| 4195 |
+
{
|
| 4196 |
+
"epoch": 0.1618181818181818,
|
| 4197 |
+
"grad_norm": 0.14446097612380981,
|
| 4198 |
+
"learning_rate": 0.0005182420690557091,
|
| 4199 |
+
"loss": 2.6884750366210937,
|
| 4200 |
+
"step": 53800
|
| 4201 |
+
},
|
| 4202 |
+
{
|
| 4203 |
+
"epoch": 0.16272727272727272,
|
| 4204 |
+
"grad_norm": 0.14465349912643433,
|
| 4205 |
+
"learning_rate": 0.0005168130018273655,
|
| 4206 |
+
"loss": 2.677554931640625,
|
| 4207 |
+
"step": 53900
|
| 4208 |
+
},
|
| 4209 |
+
{
|
| 4210 |
+
"epoch": 0.16363636363636364,
|
| 4211 |
+
"grad_norm": 0.14523738622665405,
|
| 4212 |
+
"learning_rate": 0.0005153837970857591,
|
| 4213 |
+
"loss": 2.66891357421875,
|
| 4214 |
+
"step": 54000
|
| 4215 |
+
},
|
| 4216 |
+
{
|
| 4217 |
+
"epoch": 0.16363636363636364,
|
| 4218 |
+
"eval_loss": 3.070340394973755,
|
| 4219 |
+
"eval_runtime": 7.4203,
|
| 4220 |
+
"eval_samples_per_second": 77.625,
|
| 4221 |
+
"eval_steps_per_second": 19.406,
|
| 4222 |
+
"step": 54000
|
| 4223 |
+
},
|
| 4224 |
+
{
|
| 4225 |
+
"epoch": 0.16454545454545455,
|
| 4226 |
+
"grad_norm": 0.14817142486572266,
|
| 4227 |
+
"learning_rate": 0.0005139544665203315,
|
| 4228 |
+
"loss": 2.69839599609375,
|
| 4229 |
+
"step": 54100
|
| 4230 |
+
},
|
| 4231 |
+
{
|
| 4232 |
+
"epoch": 0.16545454545454547,
|
| 4233 |
+
"grad_norm": 0.18234474956989288,
|
| 4234 |
+
"learning_rate": 0.0005125250218215538,
|
| 4235 |
+
"loss": 2.667855224609375,
|
| 4236 |
+
"step": 54200
|
| 4237 |
+
},
|
| 4238 |
+
{
|
| 4239 |
+
"epoch": 0.16636363636363635,
|
| 4240 |
+
"grad_norm": 0.16814777255058289,
|
| 4241 |
+
"learning_rate": 0.0005110954746808307,
|
| 4242 |
+
"loss": 2.683269348144531,
|
| 4243 |
+
"step": 54300
|
| 4244 |
+
},
|
| 4245 |
+
{
|
| 4246 |
+
"epoch": 0.16727272727272727,
|
| 4247 |
+
"grad_norm": 0.1632496416568756,
|
| 4248 |
+
"learning_rate": 0.0005096658367904042,
|
| 4249 |
+
"loss": 2.670632629394531,
|
| 4250 |
+
"step": 54400
|
| 4251 |
+
},
|
| 4252 |
+
{
|
| 4253 |
+
"epoch": 0.16818181818181818,
|
| 4254 |
+
"grad_norm": 0.15290036797523499,
|
| 4255 |
+
"learning_rate": 0.0005082361198432592,
|
| 4256 |
+
"loss": 2.6895196533203123,
|
| 4257 |
+
"step": 54500
|
| 4258 |
+
},
|
| 4259 |
+
{
|
| 4260 |
+
"epoch": 0.1690909090909091,
|
| 4261 |
+
"grad_norm": 0.15638327598571777,
|
| 4262 |
+
"learning_rate": 0.0005068063355330264,
|
| 4263 |
+
"loss": 2.676280212402344,
|
| 4264 |
+
"step": 54600
|
| 4265 |
+
},
|
| 4266 |
+
{
|
| 4267 |
+
"epoch": 0.17,
|
| 4268 |
+
"grad_norm": 0.14327116310596466,
|
| 4269 |
+
"learning_rate": 0.0005053764955538885,
|
| 4270 |
+
"loss": 2.693046875,
|
| 4271 |
+
"step": 54700
|
| 4272 |
+
},
|
| 4273 |
+
{
|
| 4274 |
+
"epoch": 0.1709090909090909,
|
| 4275 |
+
"grad_norm": 0.1540258675813675,
|
| 4276 |
+
"learning_rate": 0.0005039466116004827,
|
| 4277 |
+
"loss": 2.6647442626953124,
|
| 4278 |
+
"step": 54800
|
| 4279 |
+
},
|
| 4280 |
+
{
|
| 4281 |
+
"epoch": 0.17181818181818181,
|
| 4282 |
+
"grad_norm": 0.14872531592845917,
|
| 4283 |
+
"learning_rate": 0.0005025166953678061,
|
| 4284 |
+
"loss": 2.669239501953125,
|
| 4285 |
+
"step": 54900
|
| 4286 |
+
},
|
| 4287 |
+
{
|
| 4288 |
+
"epoch": 0.17272727272727273,
|
| 4289 |
+
"grad_norm": 0.15456752479076385,
|
| 4290 |
+
"learning_rate": 0.0005010867585511199,
|
| 4291 |
+
"loss": 2.6779644775390623,
|
| 4292 |
+
"step": 55000
|
| 4293 |
+
},
|
| 4294 |
+
{
|
| 4295 |
+
"epoch": 0.17272727272727273,
|
| 4296 |
+
"eval_loss": 3.070594072341919,
|
| 4297 |
+
"eval_runtime": 7.4584,
|
| 4298 |
+
"eval_samples_per_second": 77.229,
|
| 4299 |
+
"eval_steps_per_second": 19.307,
|
| 4300 |
+
"step": 55000
|
| 4301 |
+
},
|
| 4302 |
+
{
|
| 4303 |
+
"epoch": 0.17363636363636364,
|
| 4304 |
+
"grad_norm": 0.14803044497966766,
|
| 4305 |
+
"learning_rate": 0.0004996568128458535,
|
| 4306 |
+
"loss": 2.698114013671875,
|
| 4307 |
+
"step": 55100
|
| 4308 |
+
},
|
| 4309 |
+
{
|
| 4310 |
+
"epoch": 0.17454545454545456,
|
| 4311 |
+
"grad_norm": 0.14924941956996918,
|
| 4312 |
+
"learning_rate": 0.0004982268699475092,
|
| 4313 |
+
"loss": 2.638841247558594,
|
| 4314 |
+
"step": 55200
|
| 4315 |
+
},
|
| 4316 |
+
{
|
| 4317 |
+
"epoch": 0.17545454545454545,
|
| 4318 |
+
"grad_norm": 0.15640807151794434,
|
| 4319 |
+
"learning_rate": 0.0004967969415515659,
|
| 4320 |
+
"loss": 2.6517404174804686,
|
| 4321 |
+
"step": 55300
|
| 4322 |
+
},
|
| 4323 |
+
{
|
| 4324 |
+
"epoch": 0.17636363636363636,
|
| 4325 |
+
"grad_norm": 0.18078777194023132,
|
| 4326 |
+
"learning_rate": 0.0004953670393533846,
|
| 4327 |
+
"loss": 2.6669937133789063,
|
| 4328 |
+
"step": 55400
|
| 4329 |
+
},
|
| 4330 |
+
{
|
| 4331 |
+
"epoch": 0.17727272727272728,
|
| 4332 |
+
"grad_norm": 0.15050143003463745,
|
| 4333 |
+
"learning_rate": 0.0004939371750481115,
|
| 4334 |
+
"loss": 2.6495355224609374,
|
| 4335 |
+
"step": 55500
|
| 4336 |
+
},
|
| 4337 |
+
{
|
| 4338 |
+
"epoch": 0.1781818181818182,
|
| 4339 |
+
"grad_norm": 0.15939530730247498,
|
| 4340 |
+
"learning_rate": 0.0004925073603305833,
|
| 4341 |
+
"loss": 2.673974609375,
|
| 4342 |
+
"step": 55600
|
| 4343 |
+
},
|
| 4344 |
+
{
|
| 4345 |
+
"epoch": 0.17909090909090908,
|
| 4346 |
+
"grad_norm": 0.7551309466362,
|
| 4347 |
+
"learning_rate": 0.0004910776068952304,
|
| 4348 |
+
"loss": 2.6610736083984374,
|
| 4349 |
+
"step": 55700
|
| 4350 |
+
},
|
| 4351 |
+
{
|
| 4352 |
+
"epoch": 0.18,
|
| 4353 |
+
"grad_norm": 0.14220239222049713,
|
| 4354 |
+
"learning_rate": 0.0004896479264359827,
|
| 4355 |
+
"loss": 2.7120089721679688,
|
| 4356 |
+
"step": 55800
|
| 4357 |
+
},
|
| 4358 |
+
{
|
| 4359 |
+
"epoch": 0.1809090909090909,
|
| 4360 |
+
"grad_norm": 0.17650385200977325,
|
| 4361 |
+
"learning_rate": 0.0004882183306461728,
|
| 4362 |
+
"loss": 2.6712158203125,
|
| 4363 |
+
"step": 55900
|
| 4364 |
+
},
|
| 4365 |
+
{
|
| 4366 |
+
"epoch": 0.18181818181818182,
|
| 4367 |
+
"grad_norm": 0.15496277809143066,
|
| 4368 |
+
"learning_rate": 0.00048678883121844096,
|
| 4369 |
+
"loss": 2.6805792236328125,
|
| 4370 |
+
"step": 56000
|
| 4371 |
+
},
|
| 4372 |
+
{
|
| 4373 |
+
"epoch": 0.18181818181818182,
|
| 4374 |
+
"eval_loss": 3.068009614944458,
|
| 4375 |
+
"eval_runtime": 7.4586,
|
| 4376 |
+
"eval_samples_per_second": 77.227,
|
| 4377 |
+
"eval_steps_per_second": 19.307,
|
| 4378 |
+
"step": 56000
|
| 4379 |
}
|
| 4380 |
],
|
| 4381 |
"logging_steps": 100,
|
|
|
|
| 4395 |
"attributes": {}
|
| 4396 |
}
|
| 4397 |
},
|
| 4398 |
+
"total_flos": 1.395216535781376e+18,
|
| 4399 |
"train_batch_size": 22,
|
| 4400 |
"trial_name": null,
|
| 4401 |
"trial_params": null
|