Training in progress, step 48000, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3555504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a65415a9d174aeb6628f2a1f3312063a7b378d9e9b6140f0c42d8a550caf91d7
|
| 3 |
size 3555504
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7141515
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd517c20ac98c90d8ce6f5887bb515507de628ca9fd8fe91aa578d3677906648
|
| 3 |
size 7141515
|
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:ba01fbde1e06f07c52269f0f4ecd17f79378b8843a5ca873c42d0450dd248933
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2506b019d401bb5719d882cc120b44ae3c311583a2faec565dae037f51160d5
|
| 3 |
size 1383
|
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:b0c8e4e92a6a4d6dc0cfaa1d114795a3cfc8bb22eeb20851eec07e893ae0e183
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 44000,
|
| 3 |
"best_metric": 0.9900904784547742,
|
| 4 |
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-44000",
|
| 5 |
-
"epoch": 1.
|
| 6 |
"eval_steps": 4000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3220,6 +3220,298 @@
|
|
| 3220 |
"eval_samples_per_second": 129.014,
|
| 3221 |
"eval_steps_per_second": 8.063,
|
| 3222 |
"step": 44000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3223 |
}
|
| 3224 |
],
|
| 3225 |
"logging_steps": 100,
|
|
@@ -3234,7 +3526,7 @@
|
|
| 3234 |
"early_stopping_threshold": 0.0
|
| 3235 |
},
|
| 3236 |
"attributes": {
|
| 3237 |
-
"early_stopping_patience_counter":
|
| 3238 |
}
|
| 3239 |
},
|
| 3240 |
"TrainerControl": {
|
|
@@ -3248,7 +3540,7 @@
|
|
| 3248 |
"attributes": {}
|
| 3249 |
}
|
| 3250 |
},
|
| 3251 |
-
"total_flos":
|
| 3252 |
"train_batch_size": 16,
|
| 3253 |
"trial_name": null,
|
| 3254 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 44000,
|
| 3 |
"best_metric": 0.9900904784547742,
|
| 4 |
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-44000",
|
| 5 |
+
"epoch": 1.536,
|
| 6 |
"eval_steps": 4000,
|
| 7 |
+
"global_step": 48000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3220 |
"eval_samples_per_second": 129.014,
|
| 3221 |
"eval_steps_per_second": 8.063,
|
| 3222 |
"step": 44000
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 1.4112,
|
| 3226 |
+
"grad_norm": 0.6451414823532104,
|
| 3227 |
+
"learning_rate": 1.4401412520064206e-05,
|
| 3228 |
+
"loss": 0.044,
|
| 3229 |
+
"step": 44100
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 1.4144,
|
| 3233 |
+
"grad_norm": 0.03619956597685814,
|
| 3234 |
+
"learning_rate": 1.438857142857143e-05,
|
| 3235 |
+
"loss": 0.0386,
|
| 3236 |
+
"step": 44200
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 1.4176,
|
| 3240 |
+
"grad_norm": 0.005635638255625963,
|
| 3241 |
+
"learning_rate": 1.4375730337078653e-05,
|
| 3242 |
+
"loss": 0.0371,
|
| 3243 |
+
"step": 44300
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 1.4208,
|
| 3247 |
+
"grad_norm": 20.394947052001953,
|
| 3248 |
+
"learning_rate": 1.4362889245585876e-05,
|
| 3249 |
+
"loss": 0.0468,
|
| 3250 |
+
"step": 44400
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 1.424,
|
| 3254 |
+
"grad_norm": 0.008449492044746876,
|
| 3255 |
+
"learning_rate": 1.4350048154093099e-05,
|
| 3256 |
+
"loss": 0.0536,
|
| 3257 |
+
"step": 44500
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 1.4272,
|
| 3261 |
+
"grad_norm": 0.06385083496570587,
|
| 3262 |
+
"learning_rate": 1.4337207062600322e-05,
|
| 3263 |
+
"loss": 0.0383,
|
| 3264 |
+
"step": 44600
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 1.4304000000000001,
|
| 3268 |
+
"grad_norm": 0.016077406704425812,
|
| 3269 |
+
"learning_rate": 1.4324365971107545e-05,
|
| 3270 |
+
"loss": 0.0341,
|
| 3271 |
+
"step": 44700
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 1.4336,
|
| 3275 |
+
"grad_norm": 0.012415707111358643,
|
| 3276 |
+
"learning_rate": 1.4311524879614768e-05,
|
| 3277 |
+
"loss": 0.0356,
|
| 3278 |
+
"step": 44800
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 1.4368,
|
| 3282 |
+
"grad_norm": 0.03126490116119385,
|
| 3283 |
+
"learning_rate": 1.4298683788121991e-05,
|
| 3284 |
+
"loss": 0.0456,
|
| 3285 |
+
"step": 44900
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 1.44,
|
| 3289 |
+
"grad_norm": 5.324023723602295,
|
| 3290 |
+
"learning_rate": 1.4285842696629215e-05,
|
| 3291 |
+
"loss": 0.0653,
|
| 3292 |
+
"step": 45000
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 1.4432,
|
| 3296 |
+
"grad_norm": 0.02962222322821617,
|
| 3297 |
+
"learning_rate": 1.4273001605136438e-05,
|
| 3298 |
+
"loss": 0.0664,
|
| 3299 |
+
"step": 45100
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 1.4464000000000001,
|
| 3303 |
+
"grad_norm": 0.03100472316145897,
|
| 3304 |
+
"learning_rate": 1.426016051364366e-05,
|
| 3305 |
+
"loss": 0.0494,
|
| 3306 |
+
"step": 45200
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 1.4496,
|
| 3310 |
+
"grad_norm": 8.572321891784668,
|
| 3311 |
+
"learning_rate": 1.4247319422150884e-05,
|
| 3312 |
+
"loss": 0.0276,
|
| 3313 |
+
"step": 45300
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 1.4527999999999999,
|
| 3317 |
+
"grad_norm": 0.004455466754734516,
|
| 3318 |
+
"learning_rate": 1.4234478330658109e-05,
|
| 3319 |
+
"loss": 0.0292,
|
| 3320 |
+
"step": 45400
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 1.456,
|
| 3324 |
+
"grad_norm": 0.03781688213348389,
|
| 3325 |
+
"learning_rate": 1.4221637239165332e-05,
|
| 3326 |
+
"loss": 0.0407,
|
| 3327 |
+
"step": 45500
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 1.4592,
|
| 3331 |
+
"grad_norm": 10.108696937561035,
|
| 3332 |
+
"learning_rate": 1.4208796147672552e-05,
|
| 3333 |
+
"loss": 0.0531,
|
| 3334 |
+
"step": 45600
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 1.4624,
|
| 3338 |
+
"grad_norm": 0.059839170426130295,
|
| 3339 |
+
"learning_rate": 1.4195955056179775e-05,
|
| 3340 |
+
"loss": 0.0373,
|
| 3341 |
+
"step": 45700
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 1.4656,
|
| 3345 |
+
"grad_norm": 0.00919304322451353,
|
| 3346 |
+
"learning_rate": 1.4183113964686998e-05,
|
| 3347 |
+
"loss": 0.0402,
|
| 3348 |
+
"step": 45800
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 1.4687999999999999,
|
| 3352 |
+
"grad_norm": 12.830222129821777,
|
| 3353 |
+
"learning_rate": 1.4170272873194221e-05,
|
| 3354 |
+
"loss": 0.0321,
|
| 3355 |
+
"step": 45900
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 1.472,
|
| 3359 |
+
"grad_norm": 0.006019544322043657,
|
| 3360 |
+
"learning_rate": 1.4157431781701444e-05,
|
| 3361 |
+
"loss": 0.0327,
|
| 3362 |
+
"step": 46000
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 1.4752,
|
| 3366 |
+
"grad_norm": 0.024647433310747147,
|
| 3367 |
+
"learning_rate": 1.4144590690208669e-05,
|
| 3368 |
+
"loss": 0.0386,
|
| 3369 |
+
"step": 46100
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 1.4784,
|
| 3373 |
+
"grad_norm": 0.01691538281738758,
|
| 3374 |
+
"learning_rate": 1.4131749598715892e-05,
|
| 3375 |
+
"loss": 0.0523,
|
| 3376 |
+
"step": 46200
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 1.4816,
|
| 3380 |
+
"grad_norm": 0.007636231370270252,
|
| 3381 |
+
"learning_rate": 1.4118908507223115e-05,
|
| 3382 |
+
"loss": 0.043,
|
| 3383 |
+
"step": 46300
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 1.4848,
|
| 3387 |
+
"grad_norm": 0.04239976033568382,
|
| 3388 |
+
"learning_rate": 1.4106067415730338e-05,
|
| 3389 |
+
"loss": 0.0422,
|
| 3390 |
+
"step": 46400
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 1.488,
|
| 3394 |
+
"grad_norm": 6.693536758422852,
|
| 3395 |
+
"learning_rate": 1.4093226324237562e-05,
|
| 3396 |
+
"loss": 0.0412,
|
| 3397 |
+
"step": 46500
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 1.4912,
|
| 3401 |
+
"grad_norm": 0.014838839881122112,
|
| 3402 |
+
"learning_rate": 1.4080385232744785e-05,
|
| 3403 |
+
"loss": 0.038,
|
| 3404 |
+
"step": 46600
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 1.4944,
|
| 3408 |
+
"grad_norm": 9.719799995422363,
|
| 3409 |
+
"learning_rate": 1.4067544141252008e-05,
|
| 3410 |
+
"loss": 0.056,
|
| 3411 |
+
"step": 46700
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 1.4976,
|
| 3415 |
+
"grad_norm": 4.120741367340088,
|
| 3416 |
+
"learning_rate": 1.4054703049759231e-05,
|
| 3417 |
+
"loss": 0.0453,
|
| 3418 |
+
"step": 46800
|
| 3419 |
+
},
|
| 3420 |
+
{
|
| 3421 |
+
"epoch": 1.5008,
|
| 3422 |
+
"grad_norm": 0.019338663667440414,
|
| 3423 |
+
"learning_rate": 1.4041861958266454e-05,
|
| 3424 |
+
"loss": 0.0355,
|
| 3425 |
+
"step": 46900
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 1.504,
|
| 3429 |
+
"grad_norm": 0.015643298625946045,
|
| 3430 |
+
"learning_rate": 1.4029020866773677e-05,
|
| 3431 |
+
"loss": 0.0276,
|
| 3432 |
+
"step": 47000
|
| 3433 |
+
},
|
| 3434 |
+
{
|
| 3435 |
+
"epoch": 1.5072,
|
| 3436 |
+
"grad_norm": 11.701508522033691,
|
| 3437 |
+
"learning_rate": 1.40161797752809e-05,
|
| 3438 |
+
"loss": 0.0513,
|
| 3439 |
+
"step": 47100
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 1.5104,
|
| 3443 |
+
"grad_norm": 0.00980925839394331,
|
| 3444 |
+
"learning_rate": 1.4003338683788124e-05,
|
| 3445 |
+
"loss": 0.0304,
|
| 3446 |
+
"step": 47200
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 1.5135999999999998,
|
| 3450 |
+
"grad_norm": 0.018979301676154137,
|
| 3451 |
+
"learning_rate": 1.3990497592295347e-05,
|
| 3452 |
+
"loss": 0.0443,
|
| 3453 |
+
"step": 47300
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 1.5168,
|
| 3457 |
+
"grad_norm": 9.20014762878418,
|
| 3458 |
+
"learning_rate": 1.397765650080257e-05,
|
| 3459 |
+
"loss": 0.0411,
|
| 3460 |
+
"step": 47400
|
| 3461 |
+
},
|
| 3462 |
+
{
|
| 3463 |
+
"epoch": 1.52,
|
| 3464 |
+
"grad_norm": 0.06917817145586014,
|
| 3465 |
+
"learning_rate": 1.3964815409309793e-05,
|
| 3466 |
+
"loss": 0.0414,
|
| 3467 |
+
"step": 47500
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 1.5232,
|
| 3471 |
+
"grad_norm": 22.683095932006836,
|
| 3472 |
+
"learning_rate": 1.3951974317817016e-05,
|
| 3473 |
+
"loss": 0.0338,
|
| 3474 |
+
"step": 47600
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"epoch": 1.5264,
|
| 3478 |
+
"grad_norm": 0.03558173030614853,
|
| 3479 |
+
"learning_rate": 1.393913322632424e-05,
|
| 3480 |
+
"loss": 0.0396,
|
| 3481 |
+
"step": 47700
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 1.5295999999999998,
|
| 3485 |
+
"grad_norm": 0.12180989980697632,
|
| 3486 |
+
"learning_rate": 1.3926292134831462e-05,
|
| 3487 |
+
"loss": 0.0359,
|
| 3488 |
+
"step": 47800
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 1.5328,
|
| 3492 |
+
"grad_norm": 2.8462178707122803,
|
| 3493 |
+
"learning_rate": 1.3913451043338686e-05,
|
| 3494 |
+
"loss": 0.0234,
|
| 3495 |
+
"step": 47900
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 1.536,
|
| 3499 |
+
"grad_norm": 0.032463911920785904,
|
| 3500 |
+
"learning_rate": 1.3900609951845907e-05,
|
| 3501 |
+
"loss": 0.0389,
|
| 3502 |
+
"step": 48000
|
| 3503 |
+
},
|
| 3504 |
+
{
|
| 3505 |
+
"epoch": 1.536,
|
| 3506 |
+
"eval_accuracy": 0.98882,
|
| 3507 |
+
"eval_f1": 0.9888222770915966,
|
| 3508 |
+
"eval_loss": 0.051280781626701355,
|
| 3509 |
+
"eval_precision": 0.9888728773724597,
|
| 3510 |
+
"eval_recall": 0.98882,
|
| 3511 |
+
"eval_runtime": 775.3173,
|
| 3512 |
+
"eval_samples_per_second": 128.979,
|
| 3513 |
+
"eval_steps_per_second": 8.061,
|
| 3514 |
+
"step": 48000
|
| 3515 |
}
|
| 3516 |
],
|
| 3517 |
"logging_steps": 100,
|
|
|
|
| 3526 |
"early_stopping_threshold": 0.0
|
| 3527 |
},
|
| 3528 |
"attributes": {
|
| 3529 |
+
"early_stopping_patience_counter": 1
|
| 3530 |
}
|
| 3531 |
},
|
| 3532 |
"TrainerControl": {
|
|
|
|
| 3540 |
"attributes": {}
|
| 3541 |
}
|
| 3542 |
},
|
| 3543 |
+
"total_flos": 2.0383461668418547e+17,
|
| 3544 |
"train_batch_size": 16,
|
| 3545 |
"trial_name": null,
|
| 3546 |
"trial_params": null
|