Training in progress, step 44000, 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 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0302f359737a0861a08d5300ffbacaf83fa3a8be231fe4f4d1d48ec4bc868703
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0c65dd0b573072496bd5c019f7a3adc94aeef2c65e8f10a440ac060ae875a09
|
| 3 |
size 1082379659
|
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 sha256:2ff17261e7b5e5b975d26b5586b146fae1f6df93e96d395e1220068624854c3c
|
| 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 sha256:52822ae525808556d105455f8693d96c34e031a74ca2ba13cffb17b581b87cf5
|
| 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,
|
|
@@ -3128,6 +3128,318 @@
|
|
| 3128 |
"eval_samples_per_second": 36.502,
|
| 3129 |
"eval_steps_per_second": 9.125,
|
| 3130 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3131 |
}
|
| 3132 |
],
|
| 3133 |
"logging_steps": 100,
|
|
@@ -3147,7 +3459,7 @@
|
|
| 3147 |
"attributes": {}
|
| 3148 |
}
|
| 3149 |
},
|
| 3150 |
-
"total_flos": 1.
|
| 3151 |
"train_batch_size": 22,
|
| 3152 |
"trial_name": null,
|
| 3153 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5714285714285714,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 44000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3128 |
"eval_samples_per_second": 36.502,
|
| 3129 |
"eval_steps_per_second": 9.125,
|
| 3130 |
"step": 40000
|
| 3131 |
+
},
|
| 3132 |
+
{
|
| 3133 |
+
"epoch": 0.5207792207792208,
|
| 3134 |
+
"grad_norm": 0.22620290517807007,
|
| 3135 |
+
"learning_rate": 0.0007151438460054607,
|
| 3136 |
+
"loss": 2.7895,
|
| 3137 |
+
"step": 40100
|
| 3138 |
+
},
|
| 3139 |
+
{
|
| 3140 |
+
"epoch": 0.522077922077922,
|
| 3141 |
+
"grad_norm": 0.21930238604545593,
|
| 3142 |
+
"learning_rate": 0.000713841489430064,
|
| 3143 |
+
"loss": 2.7593,
|
| 3144 |
+
"step": 40200
|
| 3145 |
+
},
|
| 3146 |
+
{
|
| 3147 |
+
"epoch": 0.5233766233766234,
|
| 3148 |
+
"grad_norm": 0.232050359249115,
|
| 3149 |
+
"learning_rate": 0.0007125373548334219,
|
| 3150 |
+
"loss": 2.7341,
|
| 3151 |
+
"step": 40300
|
| 3152 |
+
},
|
| 3153 |
+
{
|
| 3154 |
+
"epoch": 0.5246753246753246,
|
| 3155 |
+
"grad_norm": 0.22093582153320312,
|
| 3156 |
+
"learning_rate": 0.0007112314530589825,
|
| 3157 |
+
"loss": 2.7415,
|
| 3158 |
+
"step": 40400
|
| 3159 |
+
},
|
| 3160 |
+
{
|
| 3161 |
+
"epoch": 0.525974025974026,
|
| 3162 |
+
"grad_norm": 0.21834588050842285,
|
| 3163 |
+
"learning_rate": 0.0007099237949648867,
|
| 3164 |
+
"loss": 2.7734,
|
| 3165 |
+
"step": 40500
|
| 3166 |
+
},
|
| 3167 |
+
{
|
| 3168 |
+
"epoch": 0.5272727272727272,
|
| 3169 |
+
"grad_norm": 0.2412509173154831,
|
| 3170 |
+
"learning_rate": 0.0007086143914238792,
|
| 3171 |
+
"loss": 2.7344,
|
| 3172 |
+
"step": 40600
|
| 3173 |
+
},
|
| 3174 |
+
{
|
| 3175 |
+
"epoch": 0.5285714285714286,
|
| 3176 |
+
"grad_norm": 0.2703639268875122,
|
| 3177 |
+
"learning_rate": 0.0007073032533232172,
|
| 3178 |
+
"loss": 2.7758,
|
| 3179 |
+
"step": 40700
|
| 3180 |
+
},
|
| 3181 |
+
{
|
| 3182 |
+
"epoch": 0.5298701298701298,
|
| 3183 |
+
"grad_norm": 0.26110807061195374,
|
| 3184 |
+
"learning_rate": 0.0007059903915645802,
|
| 3185 |
+
"loss": 2.7708,
|
| 3186 |
+
"step": 40800
|
| 3187 |
+
},
|
| 3188 |
+
{
|
| 3189 |
+
"epoch": 0.5311688311688312,
|
| 3190 |
+
"grad_norm": 0.2253560870885849,
|
| 3191 |
+
"learning_rate": 0.0007046758170639795,
|
| 3192 |
+
"loss": 2.7728,
|
| 3193 |
+
"step": 40900
|
| 3194 |
+
},
|
| 3195 |
+
{
|
| 3196 |
+
"epoch": 0.5324675324675324,
|
| 3197 |
+
"grad_norm": 0.2106214314699173,
|
| 3198 |
+
"learning_rate": 0.0007033595407516674,
|
| 3199 |
+
"loss": 2.7487,
|
| 3200 |
+
"step": 41000
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"epoch": 0.5324675324675324,
|
| 3204 |
+
"eval_loss": 3.1333227157592773,
|
| 3205 |
+
"eval_runtime": 15.8871,
|
| 3206 |
+
"eval_samples_per_second": 36.256,
|
| 3207 |
+
"eval_steps_per_second": 9.064,
|
| 3208 |
+
"step": 41000
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 0.5337662337662338,
|
| 3212 |
+
"grad_norm": 0.21964064240455627,
|
| 3213 |
+
"learning_rate": 0.0007020415735720458,
|
| 3214 |
+
"loss": 2.7644,
|
| 3215 |
+
"step": 41100
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.535064935064935,
|
| 3219 |
+
"grad_norm": 0.2143610268831253,
|
| 3220 |
+
"learning_rate": 0.0007007219264835758,
|
| 3221 |
+
"loss": 2.7476,
|
| 3222 |
+
"step": 41200
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 0.5363636363636364,
|
| 3226 |
+
"grad_norm": 0.3317408263683319,
|
| 3227 |
+
"learning_rate": 0.0006994006104586865,
|
| 3228 |
+
"loss": 2.7193,
|
| 3229 |
+
"step": 41300
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.5376623376623376,
|
| 3233 |
+
"grad_norm": 0.2196430265903473,
|
| 3234 |
+
"learning_rate": 0.0006980776364836834,
|
| 3235 |
+
"loss": 2.7699,
|
| 3236 |
+
"step": 41400
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.538961038961039,
|
| 3240 |
+
"grad_norm": 0.2349650114774704,
|
| 3241 |
+
"learning_rate": 0.0006967530155586577,
|
| 3242 |
+
"loss": 2.7812,
|
| 3243 |
+
"step": 41500
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 0.5402597402597402,
|
| 3247 |
+
"grad_norm": 0.20911413431167603,
|
| 3248 |
+
"learning_rate": 0.0006954267586973939,
|
| 3249 |
+
"loss": 2.7562,
|
| 3250 |
+
"step": 41600
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 0.5415584415584416,
|
| 3254 |
+
"grad_norm": 0.2115071713924408,
|
| 3255 |
+
"learning_rate": 0.0006940988769272794,
|
| 3256 |
+
"loss": 2.7577,
|
| 3257 |
+
"step": 41700
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 0.5428571428571428,
|
| 3261 |
+
"grad_norm": 0.24407769739627838,
|
| 3262 |
+
"learning_rate": 0.0006927693812892116,
|
| 3263 |
+
"loss": 2.7342,
|
| 3264 |
+
"step": 41800
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 0.5441558441558442,
|
| 3268 |
+
"grad_norm": 0.21947546303272247,
|
| 3269 |
+
"learning_rate": 0.0006914382828375068,
|
| 3270 |
+
"loss": 2.7554,
|
| 3271 |
+
"step": 41900
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.5454545454545454,
|
| 3275 |
+
"grad_norm": 0.2191598266363144,
|
| 3276 |
+
"learning_rate": 0.000690105592639809,
|
| 3277 |
+
"loss": 2.7256,
|
| 3278 |
+
"step": 42000
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.5454545454545454,
|
| 3282 |
+
"eval_loss": 3.1299455165863037,
|
| 3283 |
+
"eval_runtime": 15.1552,
|
| 3284 |
+
"eval_samples_per_second": 38.007,
|
| 3285 |
+
"eval_steps_per_second": 9.502,
|
| 3286 |
+
"step": 42000
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 0.5467532467532468,
|
| 3290 |
+
"grad_norm": 0.22920465469360352,
|
| 3291 |
+
"learning_rate": 0.0006887713217769954,
|
| 3292 |
+
"loss": 2.7328,
|
| 3293 |
+
"step": 42100
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 0.548051948051948,
|
| 3297 |
+
"grad_norm": 0.23324090242385864,
|
| 3298 |
+
"learning_rate": 0.0006874354813430874,
|
| 3299 |
+
"loss": 2.7545,
|
| 3300 |
+
"step": 42200
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 0.5493506493506494,
|
| 3304 |
+
"grad_norm": 0.21898794174194336,
|
| 3305 |
+
"learning_rate": 0.0006860980824451563,
|
| 3306 |
+
"loss": 2.7611,
|
| 3307 |
+
"step": 42300
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 0.5506493506493506,
|
| 3311 |
+
"grad_norm": 0.21969111263751984,
|
| 3312 |
+
"learning_rate": 0.0006847591362032313,
|
| 3313 |
+
"loss": 2.7413,
|
| 3314 |
+
"step": 42400
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.551948051948052,
|
| 3318 |
+
"grad_norm": 0.24275629222393036,
|
| 3319 |
+
"learning_rate": 0.0006834186537502076,
|
| 3320 |
+
"loss": 2.7421,
|
| 3321 |
+
"step": 42500
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 0.5532467532467532,
|
| 3325 |
+
"grad_norm": 0.20918132364749908,
|
| 3326 |
+
"learning_rate": 0.0006820766462317534,
|
| 3327 |
+
"loss": 2.73,
|
| 3328 |
+
"step": 42600
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 0.5545454545454546,
|
| 3332 |
+
"grad_norm": 0.2445412427186966,
|
| 3333 |
+
"learning_rate": 0.0006807331248062174,
|
| 3334 |
+
"loss": 2.7811,
|
| 3335 |
+
"step": 42700
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 0.5558441558441558,
|
| 3339 |
+
"grad_norm": 0.24175776541233063,
|
| 3340 |
+
"learning_rate": 0.0006793881006445354,
|
| 3341 |
+
"loss": 2.7529,
|
| 3342 |
+
"step": 42800
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 0.5571428571428572,
|
| 3346 |
+
"grad_norm": 0.234651118516922,
|
| 3347 |
+
"learning_rate": 0.0006780415849301388,
|
| 3348 |
+
"loss": 2.7592,
|
| 3349 |
+
"step": 42900
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 0.5584415584415584,
|
| 3353 |
+
"grad_norm": 0.24966347217559814,
|
| 3354 |
+
"learning_rate": 0.0006766935888588599,
|
| 3355 |
+
"loss": 2.7314,
|
| 3356 |
+
"step": 43000
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 0.5584415584415584,
|
| 3360 |
+
"eval_loss": 3.1258981227874756,
|
| 3361 |
+
"eval_runtime": 15.1058,
|
| 3362 |
+
"eval_samples_per_second": 38.131,
|
| 3363 |
+
"eval_steps_per_second": 9.533,
|
| 3364 |
+
"step": 43000
|
| 3365 |
+
},
|
| 3366 |
+
{
|
| 3367 |
+
"epoch": 0.5597402597402598,
|
| 3368 |
+
"grad_norm": 0.30740296840667725,
|
| 3369 |
+
"learning_rate": 0.0006753441236388405,
|
| 3370 |
+
"loss": 2.7467,
|
| 3371 |
+
"step": 43100
|
| 3372 |
+
},
|
| 3373 |
+
{
|
| 3374 |
+
"epoch": 0.561038961038961,
|
| 3375 |
+
"grad_norm": 0.2325826734304428,
|
| 3376 |
+
"learning_rate": 0.0006739932004904373,
|
| 3377 |
+
"loss": 2.7428,
|
| 3378 |
+
"step": 43200
|
| 3379 |
+
},
|
| 3380 |
+
{
|
| 3381 |
+
"epoch": 0.5623376623376624,
|
| 3382 |
+
"grad_norm": 0.2326454520225525,
|
| 3383 |
+
"learning_rate": 0.0006726408306461294,
|
| 3384 |
+
"loss": 2.7515,
|
| 3385 |
+
"step": 43300
|
| 3386 |
+
},
|
| 3387 |
+
{
|
| 3388 |
+
"epoch": 0.5636363636363636,
|
| 3389 |
+
"grad_norm": 0.24041685461997986,
|
| 3390 |
+
"learning_rate": 0.000671287025350425,
|
| 3391 |
+
"loss": 2.7339,
|
| 3392 |
+
"step": 43400
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 0.564935064935065,
|
| 3396 |
+
"grad_norm": 0.21853885054588318,
|
| 3397 |
+
"learning_rate": 0.0006699317958597668,
|
| 3398 |
+
"loss": 2.7188,
|
| 3399 |
+
"step": 43500
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 0.5662337662337662,
|
| 3403 |
+
"grad_norm": 0.32151710987091064,
|
| 3404 |
+
"learning_rate": 0.00066857515344244,
|
| 3405 |
+
"loss": 2.7317,
|
| 3406 |
+
"step": 43600
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 0.5675324675324676,
|
| 3410 |
+
"grad_norm": 0.2511979639530182,
|
| 3411 |
+
"learning_rate": 0.0006672171093784773,
|
| 3412 |
+
"loss": 2.7714,
|
| 3413 |
+
"step": 43700
|
| 3414 |
+
},
|
| 3415 |
+
{
|
| 3416 |
+
"epoch": 0.5688311688311688,
|
| 3417 |
+
"grad_norm": 0.2406754046678543,
|
| 3418 |
+
"learning_rate": 0.0006658576749595663,
|
| 3419 |
+
"loss": 2.7762,
|
| 3420 |
+
"step": 43800
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 0.5701298701298702,
|
| 3424 |
+
"grad_norm": 0.23970568180084229,
|
| 3425 |
+
"learning_rate": 0.0006644968614889538,
|
| 3426 |
+
"loss": 2.7163,
|
| 3427 |
+
"step": 43900
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 0.5714285714285714,
|
| 3431 |
+
"grad_norm": 0.23587392270565033,
|
| 3432 |
+
"learning_rate": 0.0006631346802813543,
|
| 3433 |
+
"loss": 2.7272,
|
| 3434 |
+
"step": 44000
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 0.5714285714285714,
|
| 3438 |
+
"eval_loss": 3.120995044708252,
|
| 3439 |
+
"eval_runtime": 15.2013,
|
| 3440 |
+
"eval_samples_per_second": 37.892,
|
| 3441 |
+
"eval_steps_per_second": 9.473,
|
| 3442 |
+
"step": 44000
|
| 3443 |
}
|
| 3444 |
],
|
| 3445 |
"logging_steps": 100,
|
|
|
|
| 3459 |
"attributes": {}
|
| 3460 |
}
|
| 3461 |
},
|
| 3462 |
+
"total_flos": 1.30984980774912e+18,
|
| 3463 |
"train_batch_size": 22,
|
| 3464 |
"trial_name": null,
|
| 3465 |
"trial_params": null
|