Training in progress, step 170000
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/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50044689
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:890dc581163da8ac34698455aef8e08af0d03b6c31e289a5752b729c1a6eb8ad
|
3 |
size 50044689
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25761253
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:478382e1e4afce83db55490eec55f2c2cc88645b07b91562f7bf2468273abbf0
|
3 |
size 25761253
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8bf8ede2357b1086ec56810178a0bcfed2f59612fe08e69399b2d94840600f1
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8bf8ede2357b1086ec56810178a0bcfed2f59612fe08e69399b2d94840600f1
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8bf8ede2357b1086ec56810178a0bcfed2f59612fe08e69399b2d94840600f1
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8bf8ede2357b1086ec56810178a0bcfed2f59612fe08e69399b2d94840600f1
|
3 |
size 14503
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8bf8ede2357b1086ec56810178a0bcfed2f59612fe08e69399b2d94840600f1
|
3 |
size 14503
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8bf8ede2357b1086ec56810178a0bcfed2f59612fe08e69399b2d94840600f1
|
3 |
size 14503
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8bf8ede2357b1086ec56810178a0bcfed2f59612fe08e69399b2d94840600f1
|
3 |
size 14503
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8bf8ede2357b1086ec56810178a0bcfed2f59612fe08e69399b2d94840600f1
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1470898ecdc6550560113c5e2cfd1e79edea6b27c0b7d35814645546c1b5bff0
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 7.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -3206,11 +3206,211 @@
|
|
3206 |
"eval_samples_per_second": 1000.637,
|
3207 |
"eval_steps_per_second": 15.683,
|
3208 |
"step": 160000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3209 |
}
|
3210 |
],
|
3211 |
"max_steps": 250000,
|
3212 |
"num_train_epochs": 12,
|
3213 |
-
"total_flos": 2.
|
3214 |
"trial_name": null,
|
3215 |
"trial_params": null
|
3216 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.583868665239115,
|
5 |
+
"global_step": 170000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3206 |
"eval_samples_per_second": 1000.637,
|
3207 |
"eval_steps_per_second": 15.683,
|
3208 |
"step": 160000
|
3209 |
+
},
|
3210 |
+
{
|
3211 |
+
"epoch": 7.16,
|
3212 |
+
"learning_rate": 0.00019368752321895452,
|
3213 |
+
"loss": 0.3758,
|
3214 |
+
"step": 160500
|
3215 |
+
},
|
3216 |
+
{
|
3217 |
+
"epoch": 7.18,
|
3218 |
+
"learning_rate": 0.00019188310403712105,
|
3219 |
+
"loss": 0.3756,
|
3220 |
+
"step": 161000
|
3221 |
+
},
|
3222 |
+
{
|
3223 |
+
"epoch": 7.18,
|
3224 |
+
"eval_loss": 0.3490326702594757,
|
3225 |
+
"eval_runtime": 2.2155,
|
3226 |
+
"eval_samples_per_second": 1036.763,
|
3227 |
+
"eval_steps_per_second": 16.249,
|
3228 |
+
"step": 161000
|
3229 |
+
},
|
3230 |
+
{
|
3231 |
+
"epoch": 7.2,
|
3232 |
+
"learning_rate": 0.00019008363295476495,
|
3233 |
+
"loss": 0.3756,
|
3234 |
+
"step": 161500
|
3235 |
+
},
|
3236 |
+
{
|
3237 |
+
"epoch": 7.23,
|
3238 |
+
"learning_rate": 0.0001882891886865808,
|
3239 |
+
"loss": 0.3753,
|
3240 |
+
"step": 162000
|
3241 |
+
},
|
3242 |
+
{
|
3243 |
+
"epoch": 7.23,
|
3244 |
+
"eval_loss": 0.3482523560523987,
|
3245 |
+
"eval_runtime": 2.2246,
|
3246 |
+
"eval_samples_per_second": 1032.556,
|
3247 |
+
"eval_steps_per_second": 16.183,
|
3248 |
+
"step": 162000
|
3249 |
+
},
|
3250 |
+
{
|
3251 |
+
"epoch": 7.25,
|
3252 |
+
"learning_rate": 0.00018649984972737404,
|
3253 |
+
"loss": 0.3757,
|
3254 |
+
"step": 162500
|
3255 |
+
},
|
3256 |
+
{
|
3257 |
+
"epoch": 7.27,
|
3258 |
+
"learning_rate": 0.00018471569434862749,
|
3259 |
+
"loss": 0.3749,
|
3260 |
+
"step": 163000
|
3261 |
+
},
|
3262 |
+
{
|
3263 |
+
"epoch": 7.27,
|
3264 |
+
"eval_loss": 0.3480832874774933,
|
3265 |
+
"eval_runtime": 2.1706,
|
3266 |
+
"eval_samples_per_second": 1058.217,
|
3267 |
+
"eval_steps_per_second": 16.585,
|
3268 |
+
"step": 163000
|
3269 |
+
},
|
3270 |
+
{
|
3271 |
+
"epoch": 7.29,
|
3272 |
+
"learning_rate": 0.00018293680059507713,
|
3273 |
+
"loss": 0.3753,
|
3274 |
+
"step": 163500
|
3275 |
+
},
|
3276 |
+
{
|
3277 |
+
"epoch": 7.32,
|
3278 |
+
"learning_rate": 0.00018116324628129882,
|
3279 |
+
"loss": 0.3747,
|
3280 |
+
"step": 164000
|
3281 |
+
},
|
3282 |
+
{
|
3283 |
+
"epoch": 7.32,
|
3284 |
+
"eval_loss": 0.3469808101654053,
|
3285 |
+
"eval_runtime": 2.1769,
|
3286 |
+
"eval_samples_per_second": 1055.189,
|
3287 |
+
"eval_steps_per_second": 16.538,
|
3288 |
+
"step": 164000
|
3289 |
+
},
|
3290 |
+
{
|
3291 |
+
"epoch": 7.34,
|
3292 |
+
"learning_rate": 0.00017939510898830357,
|
3293 |
+
"loss": 0.3746,
|
3294 |
+
"step": 164500
|
3295 |
+
},
|
3296 |
+
{
|
3297 |
+
"epoch": 7.36,
|
3298 |
+
"learning_rate": 0.0001776324660601446,
|
3299 |
+
"loss": 0.375,
|
3300 |
+
"step": 165000
|
3301 |
+
},
|
3302 |
+
{
|
3303 |
+
"epoch": 7.36,
|
3304 |
+
"eval_loss": 0.3475760519504547,
|
3305 |
+
"eval_runtime": 2.1442,
|
3306 |
+
"eval_samples_per_second": 1071.239,
|
3307 |
+
"eval_steps_per_second": 16.789,
|
3308 |
+
"step": 165000
|
3309 |
+
},
|
3310 |
+
{
|
3311 |
+
"epoch": 7.38,
|
3312 |
+
"learning_rate": 0.00017587539460053368,
|
3313 |
+
"loss": 0.3743,
|
3314 |
+
"step": 165500
|
3315 |
+
},
|
3316 |
+
{
|
3317 |
+
"epoch": 7.41,
|
3318 |
+
"learning_rate": 0.0001741239714694688,
|
3319 |
+
"loss": 0.3742,
|
3320 |
+
"step": 166000
|
3321 |
+
},
|
3322 |
+
{
|
3323 |
+
"epoch": 7.41,
|
3324 |
+
"eval_loss": 0.34710729122161865,
|
3325 |
+
"eval_runtime": 2.2456,
|
3326 |
+
"eval_samples_per_second": 1022.894,
|
3327 |
+
"eval_steps_per_second": 16.031,
|
3328 |
+
"step": 166000
|
3329 |
+
},
|
3330 |
+
{
|
3331 |
+
"epoch": 7.43,
|
3332 |
+
"learning_rate": 0.0001723782732798713,
|
3333 |
+
"loss": 0.3741,
|
3334 |
+
"step": 166500
|
3335 |
+
},
|
3336 |
+
{
|
3337 |
+
"epoch": 7.45,
|
3338 |
+
"learning_rate": 0.00017063837639423517,
|
3339 |
+
"loss": 0.3741,
|
3340 |
+
"step": 167000
|
3341 |
+
},
|
3342 |
+
{
|
3343 |
+
"epoch": 7.45,
|
3344 |
+
"eval_loss": 0.3461616337299347,
|
3345 |
+
"eval_runtime": 2.2634,
|
3346 |
+
"eval_samples_per_second": 1014.851,
|
3347 |
+
"eval_steps_per_second": 15.905,
|
3348 |
+
"step": 167000
|
3349 |
+
},
|
3350 |
+
{
|
3351 |
+
"epoch": 7.47,
|
3352 |
+
"learning_rate": 0.00016890435692128712,
|
3353 |
+
"loss": 0.3738,
|
3354 |
+
"step": 167500
|
3355 |
+
},
|
3356 |
+
{
|
3357 |
+
"epoch": 7.49,
|
3358 |
+
"learning_rate": 0.0001671762907126559,
|
3359 |
+
"loss": 0.3738,
|
3360 |
+
"step": 168000
|
3361 |
+
},
|
3362 |
+
{
|
3363 |
+
"epoch": 7.49,
|
3364 |
+
"eval_loss": 0.3469841480255127,
|
3365 |
+
"eval_runtime": 2.2202,
|
3366 |
+
"eval_samples_per_second": 1034.588,
|
3367 |
+
"eval_steps_per_second": 16.215,
|
3368 |
+
"step": 168000
|
3369 |
+
},
|
3370 |
+
{
|
3371 |
+
"epoch": 7.52,
|
3372 |
+
"learning_rate": 0.00016545425335955596,
|
3373 |
+
"loss": 0.3735,
|
3374 |
+
"step": 168500
|
3375 |
+
},
|
3376 |
+
{
|
3377 |
+
"epoch": 7.54,
|
3378 |
+
"learning_rate": 0.00016373832018947945,
|
3379 |
+
"loss": 0.3735,
|
3380 |
+
"step": 169000
|
3381 |
+
},
|
3382 |
+
{
|
3383 |
+
"epoch": 7.54,
|
3384 |
+
"eval_loss": 0.3462463617324829,
|
3385 |
+
"eval_runtime": 2.2185,
|
3386 |
+
"eval_samples_per_second": 1035.373,
|
3387 |
+
"eval_steps_per_second": 16.227,
|
3388 |
+
"step": 169000
|
3389 |
+
},
|
3390 |
+
{
|
3391 |
+
"epoch": 7.56,
|
3392 |
+
"learning_rate": 0.0001620285662629024,
|
3393 |
+
"loss": 0.3735,
|
3394 |
+
"step": 169500
|
3395 |
+
},
|
3396 |
+
{
|
3397 |
+
"epoch": 7.58,
|
3398 |
+
"learning_rate": 0.0001603250663700002,
|
3399 |
+
"loss": 0.3736,
|
3400 |
+
"step": 170000
|
3401 |
+
},
|
3402 |
+
{
|
3403 |
+
"epoch": 7.58,
|
3404 |
+
"eval_loss": 0.3466815948486328,
|
3405 |
+
"eval_runtime": 2.223,
|
3406 |
+
"eval_samples_per_second": 1033.305,
|
3407 |
+
"eval_steps_per_second": 16.195,
|
3408 |
+
"step": 170000
|
3409 |
}
|
3410 |
],
|
3411 |
"max_steps": 250000,
|
3412 |
"num_train_epochs": 12,
|
3413 |
+
"total_flos": 2.7228061248434544e+21,
|
3414 |
"trial_name": null,
|
3415 |
"trial_params": null
|
3416 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25761253
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:478382e1e4afce83db55490eec55f2c2cc88645b07b91562f7bf2468273abbf0
|
3 |
size 25761253
|