Commit
•
d0fc634
1
Parent(s):
024a457
Training in progress, step 5000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +363 -3
- pytorch_model.bin +1 -1
- runs/Feb11_14-00-34_74e5e7b42358/events.out.tfevents.1676124921.74e5e7b42358.292.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4115013
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35d81815d2717de634f2a36953a7237bebc0aed6d6f05bf4b444356bcd0bbcf5
|
| 3 |
size 4115013
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c87f4fb413b45320b3f6b962097316ca8762605322043e16b3d8b94d7c09674a
|
| 3 |
size 2329702453
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0d39dfe3569fd98eb88e2a2c2eaaf8e508e20a76576f7fbb2655866ff3eba6b
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6982685cb2f1f3ac97aedb27d2a37d776ee4b9327cce88693a07d917b95ae056
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -3246,11 +3246,371 @@
|
|
| 3246 |
"eval_samples_per_second": 0.238,
|
| 3247 |
"eval_steps_per_second": 0.238,
|
| 3248 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3249 |
}
|
| 3250 |
],
|
| 3251 |
"max_steps": 5060,
|
| 3252 |
"num_train_epochs": 10,
|
| 3253 |
-
"total_flos": 1.
|
| 3254 |
"trial_name": null,
|
| 3255 |
"trial_params": null
|
| 3256 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.879792873874985,
|
| 5 |
+
"global_step": 5000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 3246 |
"eval_samples_per_second": 0.238,
|
| 3247 |
"eval_steps_per_second": 0.238,
|
| 3248 |
"step": 4500
|
| 3249 |
+
},
|
| 3250 |
+
{
|
| 3251 |
+
"epoch": 8.91,
|
| 3252 |
+
"learning_rate": 5.533199195171026e-05,
|
| 3253 |
+
"loss": 0.1363,
|
| 3254 |
+
"step": 4510
|
| 3255 |
+
},
|
| 3256 |
+
{
|
| 3257 |
+
"epoch": 8.93,
|
| 3258 |
+
"learning_rate": 5.4325955734406444e-05,
|
| 3259 |
+
"loss": 0.0738,
|
| 3260 |
+
"step": 4520
|
| 3261 |
+
},
|
| 3262 |
+
{
|
| 3263 |
+
"epoch": 8.95,
|
| 3264 |
+
"learning_rate": 5.331991951710262e-05,
|
| 3265 |
+
"loss": 0.0649,
|
| 3266 |
+
"step": 4530
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 8.97,
|
| 3270 |
+
"learning_rate": 5.2313883299798795e-05,
|
| 3271 |
+
"loss": 0.0971,
|
| 3272 |
+
"step": 4540
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 8.99,
|
| 3276 |
+
"learning_rate": 5.130784708249498e-05,
|
| 3277 |
+
"loss": 0.0688,
|
| 3278 |
+
"step": 4550
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 9.01,
|
| 3282 |
+
"learning_rate": 5.030181086519115e-05,
|
| 3283 |
+
"loss": 0.0837,
|
| 3284 |
+
"step": 4560
|
| 3285 |
+
},
|
| 3286 |
+
{
|
| 3287 |
+
"epoch": 9.03,
|
| 3288 |
+
"learning_rate": 4.929577464788732e-05,
|
| 3289 |
+
"loss": 0.0891,
|
| 3290 |
+
"step": 4570
|
| 3291 |
+
},
|
| 3292 |
+
{
|
| 3293 |
+
"epoch": 9.05,
|
| 3294 |
+
"learning_rate": 4.82897384305835e-05,
|
| 3295 |
+
"loss": 0.0744,
|
| 3296 |
+
"step": 4580
|
| 3297 |
+
},
|
| 3298 |
+
{
|
| 3299 |
+
"epoch": 9.07,
|
| 3300 |
+
"learning_rate": 4.728370221327968e-05,
|
| 3301 |
+
"loss": 0.0906,
|
| 3302 |
+
"step": 4590
|
| 3303 |
+
},
|
| 3304 |
+
{
|
| 3305 |
+
"epoch": 9.09,
|
| 3306 |
+
"learning_rate": 4.6277665995975854e-05,
|
| 3307 |
+
"loss": 0.1102,
|
| 3308 |
+
"step": 4600
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 9.09,
|
| 3312 |
+
"eval_loss": 0.9806769490242004,
|
| 3313 |
+
"eval_rouge1": 0.12615384615384617,
|
| 3314 |
+
"eval_rouge2": 0.08636363636363635,
|
| 3315 |
+
"eval_rougeL": 0.13615384615384613,
|
| 3316 |
+
"eval_rougeLsum": 0.12615384615384617,
|
| 3317 |
+
"eval_runtime": 88.592,
|
| 3318 |
+
"eval_samples_per_second": 0.226,
|
| 3319 |
+
"eval_steps_per_second": 0.226,
|
| 3320 |
+
"step": 4600
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 9.11,
|
| 3324 |
+
"learning_rate": 4.527162977867203e-05,
|
| 3325 |
+
"loss": 0.072,
|
| 3326 |
+
"step": 4610
|
| 3327 |
+
},
|
| 3328 |
+
{
|
| 3329 |
+
"epoch": 9.13,
|
| 3330 |
+
"learning_rate": 4.426559356136821e-05,
|
| 3331 |
+
"loss": 0.0729,
|
| 3332 |
+
"step": 4620
|
| 3333 |
+
},
|
| 3334 |
+
{
|
| 3335 |
+
"epoch": 9.15,
|
| 3336 |
+
"learning_rate": 4.325955734406439e-05,
|
| 3337 |
+
"loss": 0.0884,
|
| 3338 |
+
"step": 4630
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 9.17,
|
| 3342 |
+
"learning_rate": 4.225352112676056e-05,
|
| 3343 |
+
"loss": 0.0782,
|
| 3344 |
+
"step": 4640
|
| 3345 |
+
},
|
| 3346 |
+
{
|
| 3347 |
+
"epoch": 9.19,
|
| 3348 |
+
"learning_rate": 4.124748490945674e-05,
|
| 3349 |
+
"loss": 0.0879,
|
| 3350 |
+
"step": 4650
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"epoch": 9.21,
|
| 3354 |
+
"learning_rate": 4.024144869215292e-05,
|
| 3355 |
+
"loss": 0.1,
|
| 3356 |
+
"step": 4660
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 9.23,
|
| 3360 |
+
"learning_rate": 3.9235412474849096e-05,
|
| 3361 |
+
"loss": 0.0867,
|
| 3362 |
+
"step": 4670
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 9.25,
|
| 3366 |
+
"learning_rate": 3.822937625754527e-05,
|
| 3367 |
+
"loss": 0.0881,
|
| 3368 |
+
"step": 4680
|
| 3369 |
+
},
|
| 3370 |
+
{
|
| 3371 |
+
"epoch": 9.27,
|
| 3372 |
+
"learning_rate": 3.7223340040241454e-05,
|
| 3373 |
+
"loss": 0.0903,
|
| 3374 |
+
"step": 4690
|
| 3375 |
+
},
|
| 3376 |
+
{
|
| 3377 |
+
"epoch": 9.29,
|
| 3378 |
+
"learning_rate": 3.621730382293763e-05,
|
| 3379 |
+
"loss": 0.0942,
|
| 3380 |
+
"step": 4700
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"epoch": 9.29,
|
| 3384 |
+
"eval_loss": 0.9865831136703491,
|
| 3385 |
+
"eval_rouge1": 0.13999999999999999,
|
| 3386 |
+
"eval_rouge2": 0.09772727272727272,
|
| 3387 |
+
"eval_rougeL": 0.14615384615384613,
|
| 3388 |
+
"eval_rougeLsum": 0.13999999999999999,
|
| 3389 |
+
"eval_runtime": 86.651,
|
| 3390 |
+
"eval_samples_per_second": 0.231,
|
| 3391 |
+
"eval_steps_per_second": 0.231,
|
| 3392 |
+
"step": 4700
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 9.31,
|
| 3396 |
+
"learning_rate": 3.5211267605633805e-05,
|
| 3397 |
+
"loss": 0.1079,
|
| 3398 |
+
"step": 4710
|
| 3399 |
+
},
|
| 3400 |
+
{
|
| 3401 |
+
"epoch": 9.33,
|
| 3402 |
+
"learning_rate": 3.420523138832998e-05,
|
| 3403 |
+
"loss": 0.0807,
|
| 3404 |
+
"step": 4720
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 9.35,
|
| 3408 |
+
"learning_rate": 3.319919517102616e-05,
|
| 3409 |
+
"loss": 0.105,
|
| 3410 |
+
"step": 4730
|
| 3411 |
+
},
|
| 3412 |
+
{
|
| 3413 |
+
"epoch": 9.37,
|
| 3414 |
+
"learning_rate": 3.219315895372234e-05,
|
| 3415 |
+
"loss": 0.095,
|
| 3416 |
+
"step": 4740
|
| 3417 |
+
},
|
| 3418 |
+
{
|
| 3419 |
+
"epoch": 9.39,
|
| 3420 |
+
"learning_rate": 3.118712273641851e-05,
|
| 3421 |
+
"loss": 0.0965,
|
| 3422 |
+
"step": 4750
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 9.41,
|
| 3426 |
+
"learning_rate": 3.018108651911469e-05,
|
| 3427 |
+
"loss": 0.1001,
|
| 3428 |
+
"step": 4760
|
| 3429 |
+
},
|
| 3430 |
+
{
|
| 3431 |
+
"epoch": 9.43,
|
| 3432 |
+
"learning_rate": 2.9175050301810868e-05,
|
| 3433 |
+
"loss": 0.0782,
|
| 3434 |
+
"step": 4770
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 9.45,
|
| 3438 |
+
"learning_rate": 2.8169014084507043e-05,
|
| 3439 |
+
"loss": 0.115,
|
| 3440 |
+
"step": 4780
|
| 3441 |
+
},
|
| 3442 |
+
{
|
| 3443 |
+
"epoch": 9.47,
|
| 3444 |
+
"learning_rate": 2.7162977867203222e-05,
|
| 3445 |
+
"loss": 0.071,
|
| 3446 |
+
"step": 4790
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 9.49,
|
| 3450 |
+
"learning_rate": 2.6156941649899397e-05,
|
| 3451 |
+
"loss": 0.129,
|
| 3452 |
+
"step": 4800
|
| 3453 |
+
},
|
| 3454 |
+
{
|
| 3455 |
+
"epoch": 9.49,
|
| 3456 |
+
"eval_loss": 0.9853466153144836,
|
| 3457 |
+
"eval_rouge1": 0.12837606837606838,
|
| 3458 |
+
"eval_rouge2": 0.08636363636363635,
|
| 3459 |
+
"eval_rougeL": 0.13615384615384613,
|
| 3460 |
+
"eval_rougeLsum": 0.1294871794871795,
|
| 3461 |
+
"eval_runtime": 86.6444,
|
| 3462 |
+
"eval_samples_per_second": 0.231,
|
| 3463 |
+
"eval_steps_per_second": 0.231,
|
| 3464 |
+
"step": 4800
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 9.5,
|
| 3468 |
+
"learning_rate": 2.5150905432595576e-05,
|
| 3469 |
+
"loss": 0.1285,
|
| 3470 |
+
"step": 4810
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 9.52,
|
| 3474 |
+
"learning_rate": 2.414486921529175e-05,
|
| 3475 |
+
"loss": 0.0747,
|
| 3476 |
+
"step": 4820
|
| 3477 |
+
},
|
| 3478 |
+
{
|
| 3479 |
+
"epoch": 9.54,
|
| 3480 |
+
"learning_rate": 2.3138832997987927e-05,
|
| 3481 |
+
"loss": 0.0702,
|
| 3482 |
+
"step": 4830
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 9.56,
|
| 3486 |
+
"learning_rate": 2.2132796780684106e-05,
|
| 3487 |
+
"loss": 0.1029,
|
| 3488 |
+
"step": 4840
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 9.58,
|
| 3492 |
+
"learning_rate": 2.112676056338028e-05,
|
| 3493 |
+
"loss": 0.102,
|
| 3494 |
+
"step": 4850
|
| 3495 |
+
},
|
| 3496 |
+
{
|
| 3497 |
+
"epoch": 9.6,
|
| 3498 |
+
"learning_rate": 2.012072434607646e-05,
|
| 3499 |
+
"loss": 0.0909,
|
| 3500 |
+
"step": 4860
|
| 3501 |
+
},
|
| 3502 |
+
{
|
| 3503 |
+
"epoch": 9.62,
|
| 3504 |
+
"learning_rate": 1.9114688128772636e-05,
|
| 3505 |
+
"loss": 0.0849,
|
| 3506 |
+
"step": 4870
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 9.64,
|
| 3510 |
+
"learning_rate": 1.8108651911468815e-05,
|
| 3511 |
+
"loss": 0.1216,
|
| 3512 |
+
"step": 4880
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 9.66,
|
| 3516 |
+
"learning_rate": 1.710261569416499e-05,
|
| 3517 |
+
"loss": 0.1016,
|
| 3518 |
+
"step": 4890
|
| 3519 |
+
},
|
| 3520 |
+
{
|
| 3521 |
+
"epoch": 9.68,
|
| 3522 |
+
"learning_rate": 1.609657947686117e-05,
|
| 3523 |
+
"loss": 0.0949,
|
| 3524 |
+
"step": 4900
|
| 3525 |
+
},
|
| 3526 |
+
{
|
| 3527 |
+
"epoch": 9.68,
|
| 3528 |
+
"eval_loss": 0.9819391965866089,
|
| 3529 |
+
"eval_rouge1": 0.1911111111111111,
|
| 3530 |
+
"eval_rouge2": 0.09772727272727272,
|
| 3531 |
+
"eval_rougeL": 0.19615384615384612,
|
| 3532 |
+
"eval_rougeLsum": 0.1923076923076923,
|
| 3533 |
+
"eval_runtime": 87.241,
|
| 3534 |
+
"eval_samples_per_second": 0.229,
|
| 3535 |
+
"eval_steps_per_second": 0.229,
|
| 3536 |
+
"step": 4900
|
| 3537 |
+
},
|
| 3538 |
+
{
|
| 3539 |
+
"epoch": 9.7,
|
| 3540 |
+
"learning_rate": 1.5090543259557344e-05,
|
| 3541 |
+
"loss": 0.0692,
|
| 3542 |
+
"step": 4910
|
| 3543 |
+
},
|
| 3544 |
+
{
|
| 3545 |
+
"epoch": 9.72,
|
| 3546 |
+
"learning_rate": 1.4084507042253522e-05,
|
| 3547 |
+
"loss": 0.0653,
|
| 3548 |
+
"step": 4920
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 9.74,
|
| 3552 |
+
"learning_rate": 1.3078470824949699e-05,
|
| 3553 |
+
"loss": 0.0797,
|
| 3554 |
+
"step": 4930
|
| 3555 |
+
},
|
| 3556 |
+
{
|
| 3557 |
+
"epoch": 9.76,
|
| 3558 |
+
"learning_rate": 1.2072434607645874e-05,
|
| 3559 |
+
"loss": 0.0905,
|
| 3560 |
+
"step": 4940
|
| 3561 |
+
},
|
| 3562 |
+
{
|
| 3563 |
+
"epoch": 9.78,
|
| 3564 |
+
"learning_rate": 1.1066398390342053e-05,
|
| 3565 |
+
"loss": 0.0868,
|
| 3566 |
+
"step": 4950
|
| 3567 |
+
},
|
| 3568 |
+
{
|
| 3569 |
+
"epoch": 9.8,
|
| 3570 |
+
"learning_rate": 1.006036217303823e-05,
|
| 3571 |
+
"loss": 0.0964,
|
| 3572 |
+
"step": 4960
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 9.82,
|
| 3576 |
+
"learning_rate": 9.054325955734407e-06,
|
| 3577 |
+
"loss": 0.0913,
|
| 3578 |
+
"step": 4970
|
| 3579 |
+
},
|
| 3580 |
+
{
|
| 3581 |
+
"epoch": 9.84,
|
| 3582 |
+
"learning_rate": 8.048289738430584e-06,
|
| 3583 |
+
"loss": 0.0708,
|
| 3584 |
+
"step": 4980
|
| 3585 |
+
},
|
| 3586 |
+
{
|
| 3587 |
+
"epoch": 9.86,
|
| 3588 |
+
"learning_rate": 7.042253521126761e-06,
|
| 3589 |
+
"loss": 0.1102,
|
| 3590 |
+
"step": 4990
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 9.88,
|
| 3594 |
+
"learning_rate": 6.036217303822937e-06,
|
| 3595 |
+
"loss": 0.0852,
|
| 3596 |
+
"step": 5000
|
| 3597 |
+
},
|
| 3598 |
+
{
|
| 3599 |
+
"epoch": 9.88,
|
| 3600 |
+
"eval_loss": 0.9852367639541626,
|
| 3601 |
+
"eval_rouge1": 0.12615384615384617,
|
| 3602 |
+
"eval_rouge2": 0.08636363636363635,
|
| 3603 |
+
"eval_rougeL": 0.13615384615384613,
|
| 3604 |
+
"eval_rougeLsum": 0.12615384615384617,
|
| 3605 |
+
"eval_runtime": 87.473,
|
| 3606 |
+
"eval_samples_per_second": 0.229,
|
| 3607 |
+
"eval_steps_per_second": 0.229,
|
| 3608 |
+
"step": 5000
|
| 3609 |
}
|
| 3610 |
],
|
| 3611 |
"max_steps": 5060,
|
| 3612 |
"num_train_epochs": 10,
|
| 3613 |
+
"total_flos": 1.2175308798022656e+17,
|
| 3614 |
"trial_name": null,
|
| 3615 |
"trial_params": null
|
| 3616 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c87f4fb413b45320b3f6b962097316ca8762605322043e16b3d8b94d7c09674a
|
| 3 |
size 2329702453
|
runs/Feb11_14-00-34_74e5e7b42358/events.out.tfevents.1676124921.74e5e7b42358.292.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23fbf43aa6b57ea727d191f2793201bb108b3520d3fbf7a5842b8ba63cc79714
|
| 3 |
+
size 24648
|