Training in progress, step 4500, 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 1482788592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89096aa0386bd07d2645f68b9a29bafea399f79871d40185060fa68039636b1f
|
| 3 |
size 1482788592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2897966842
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da854ce99198fc748d7dc94ec6e70f668228ef91b0f8c29002a2372a254620c5
|
| 3 |
size 2897966842
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2acbf6096e071e41d5582e116888a7c6ecc44cbafa614aca8be409b37f1ebc9a
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f72d12e08f2981b12196a00ff48fe5cac0ba4d9d1aa54f91464a195ecde87c8
|
| 3 |
size 1256
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "./output/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 150,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -3171,6 +3171,232 @@
|
|
| 3171 |
"eval_samples_per_second": 9.742,
|
| 3172 |
"eval_steps_per_second": 9.742,
|
| 3173 |
"step": 4200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3174 |
}
|
| 3175 |
],
|
| 3176 |
"logging_steps": 10,
|
|
@@ -3190,7 +3416,7 @@
|
|
| 3190 |
"attributes": {}
|
| 3191 |
}
|
| 3192 |
},
|
| 3193 |
-
"total_flos":
|
| 3194 |
"train_batch_size": 4,
|
| 3195 |
"trial_name": null,
|
| 3196 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.2155283689498901,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-4500",
|
| 4 |
+
"epoch": 0.297441998810232,
|
| 5 |
"eval_steps": 150,
|
| 6 |
+
"global_step": 4500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 3171 |
"eval_samples_per_second": 9.742,
|
| 3172 |
"eval_steps_per_second": 9.742,
|
| 3173 |
"step": 4200
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 0.2782735144424615,
|
| 3177 |
+
"grad_norm": 11.23477840423584,
|
| 3178 |
+
"learning_rate": 1.4037255773076804e-06,
|
| 3179 |
+
"loss": 1.0421,
|
| 3180 |
+
"step": 4210
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 0.2789344966620398,
|
| 3184 |
+
"grad_norm": 10.921051979064941,
|
| 3185 |
+
"learning_rate": 1.3691524078729481e-06,
|
| 3186 |
+
"loss": 1.055,
|
| 3187 |
+
"step": 4220
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 0.27959547888161806,
|
| 3191 |
+
"grad_norm": 7.342863082885742,
|
| 3192 |
+
"learning_rate": 1.3349825379277099e-06,
|
| 3193 |
+
"loss": 1.2973,
|
| 3194 |
+
"step": 4230
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 0.2802564611011964,
|
| 3198 |
+
"grad_norm": 11.837105751037598,
|
| 3199 |
+
"learning_rate": 1.3012173720614862e-06,
|
| 3200 |
+
"loss": 1.2177,
|
| 3201 |
+
"step": 4240
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 0.2809174433207747,
|
| 3205 |
+
"grad_norm": 13.415239334106445,
|
| 3206 |
+
"learning_rate": 1.267858298227995e-06,
|
| 3207 |
+
"loss": 1.1455,
|
| 3208 |
+
"step": 4250
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 0.28157842554035295,
|
| 3212 |
+
"grad_norm": 11.301210403442383,
|
| 3213 |
+
"learning_rate": 1.2349066876881063e-06,
|
| 3214 |
+
"loss": 1.1602,
|
| 3215 |
+
"step": 4260
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.2822394077599313,
|
| 3219 |
+
"grad_norm": 5.907723903656006,
|
| 3220 |
+
"learning_rate": 1.202363894953462e-06,
|
| 3221 |
+
"loss": 1.1053,
|
| 3222 |
+
"step": 4270
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 0.28290038997950956,
|
| 3226 |
+
"grad_norm": 12.926289558410645,
|
| 3227 |
+
"learning_rate": 1.1702312577308133e-06,
|
| 3228 |
+
"loss": 1.2056,
|
| 3229 |
+
"step": 4280
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.28356137219908784,
|
| 3233 |
+
"grad_norm": 10.026867866516113,
|
| 3234 |
+
"learning_rate": 1.1385100968670189e-06,
|
| 3235 |
+
"loss": 1.1685,
|
| 3236 |
+
"step": 4290
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.2842223544186661,
|
| 3240 |
+
"grad_norm": 12.193798065185547,
|
| 3241 |
+
"learning_rate": 1.107201716294762e-06,
|
| 3242 |
+
"loss": 1.1253,
|
| 3243 |
+
"step": 4300
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 0.28488333663824444,
|
| 3247 |
+
"grad_norm": 6.5807294845581055,
|
| 3248 |
+
"learning_rate": 1.076307402978938e-06,
|
| 3249 |
+
"loss": 1.1252,
|
| 3250 |
+
"step": 4310
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 0.2855443188578227,
|
| 3254 |
+
"grad_norm": 11.568461418151855,
|
| 3255 |
+
"learning_rate": 1.0458284268637652e-06,
|
| 3256 |
+
"loss": 1.2131,
|
| 3257 |
+
"step": 4320
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 0.286205301077401,
|
| 3261 |
+
"grad_norm": 5.46840238571167,
|
| 3262 |
+
"learning_rate": 1.0157660408205728e-06,
|
| 3263 |
+
"loss": 1.0678,
|
| 3264 |
+
"step": 4330
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 0.28686628329697933,
|
| 3268 |
+
"grad_norm": 13.20085334777832,
|
| 3269 |
+
"learning_rate": 9.861214805963042e-07,
|
| 3270 |
+
"loss": 1.1974,
|
| 3271 |
+
"step": 4340
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.2875272655165576,
|
| 3275 |
+
"grad_norm": 13.585931777954102,
|
| 3276 |
+
"learning_rate": 9.568959647627223e-07,
|
| 3277 |
+
"loss": 1.1664,
|
| 3278 |
+
"step": 4350
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.2875272655165576,
|
| 3282 |
+
"eval_loss": 1.21638822555542,
|
| 3283 |
+
"eval_runtime": 51.7738,
|
| 3284 |
+
"eval_samples_per_second": 9.677,
|
| 3285 |
+
"eval_steps_per_second": 9.677,
|
| 3286 |
+
"step": 4350
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 0.2881882477361359,
|
| 3290 |
+
"grad_norm": 7.628300189971924,
|
| 3291 |
+
"learning_rate": 9.280906946663111e-07,
|
| 3292 |
+
"loss": 1.0584,
|
| 3293 |
+
"step": 4360
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 0.2888492299557142,
|
| 3297 |
+
"grad_norm": 8.380716323852539,
|
| 3298 |
+
"learning_rate": 8.997068543789051e-07,
|
| 3299 |
+
"loss": 1.1137,
|
| 3300 |
+
"step": 4370
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 0.2895102121752925,
|
| 3304 |
+
"grad_norm": 12.071667671203613,
|
| 3305 |
+
"learning_rate": 8.717456106490042e-07,
|
| 3306 |
+
"loss": 1.0887,
|
| 3307 |
+
"step": 4380
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 0.29017119439487077,
|
| 3311 |
+
"grad_norm": 6.33940315246582,
|
| 3312 |
+
"learning_rate": 8.442081128538243e-07,
|
| 3313 |
+
"loss": 1.0145,
|
| 3314 |
+
"step": 4390
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.29083217661444905,
|
| 3318 |
+
"grad_norm": 9.972112655639648,
|
| 3319 |
+
"learning_rate": 8.170954929520389e-07,
|
| 3320 |
+
"loss": 1.1362,
|
| 3321 |
+
"step": 4400
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 0.2914931588340274,
|
| 3325 |
+
"grad_norm": 12.998346328735352,
|
| 3326 |
+
"learning_rate": 7.904088654372622e-07,
|
| 3327 |
+
"loss": 1.148,
|
| 3328 |
+
"step": 4410
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 0.29215414105360565,
|
| 3332 |
+
"grad_norm": 5.646799087524414,
|
| 3333 |
+
"learning_rate": 7.641493272922243e-07,
|
| 3334 |
+
"loss": 1.1281,
|
| 3335 |
+
"step": 4420
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 0.29281512327318393,
|
| 3339 |
+
"grad_norm": 10.702962875366211,
|
| 3340 |
+
"learning_rate": 7.383179579436903e-07,
|
| 3341 |
+
"loss": 1.1785,
|
| 3342 |
+
"step": 4430
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 0.29347610549276226,
|
| 3346 |
+
"grad_norm": 5.956870079040527,
|
| 3347 |
+
"learning_rate": 7.129158192180766e-07,
|
| 3348 |
+
"loss": 1.1568,
|
| 3349 |
+
"step": 4440
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 0.29413708771234054,
|
| 3353 |
+
"grad_norm": 11.048665046691895,
|
| 3354 |
+
"learning_rate": 6.879439552978142e-07,
|
| 3355 |
+
"loss": 1.0652,
|
| 3356 |
+
"step": 4450
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 0.2947980699319188,
|
| 3360 |
+
"grad_norm": 5.649775505065918,
|
| 3361 |
+
"learning_rate": 6.634033926784221e-07,
|
| 3362 |
+
"loss": 1.1235,
|
| 3363 |
+
"step": 4460
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 0.29545905215149715,
|
| 3367 |
+
"grad_norm": 11.055773735046387,
|
| 3368 |
+
"learning_rate": 6.392951401263069e-07,
|
| 3369 |
+
"loss": 1.285,
|
| 3370 |
+
"step": 4470
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 0.2961200343710754,
|
| 3374 |
+
"grad_norm": 7.027043342590332,
|
| 3375 |
+
"learning_rate": 6.156201886373113e-07,
|
| 3376 |
+
"loss": 1.209,
|
| 3377 |
+
"step": 4480
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 0.2967810165906537,
|
| 3381 |
+
"grad_norm": 11.43958854675293,
|
| 3382 |
+
"learning_rate": 5.923795113959569e-07,
|
| 3383 |
+
"loss": 1.2139,
|
| 3384 |
+
"step": 4490
|
| 3385 |
+
},
|
| 3386 |
+
{
|
| 3387 |
+
"epoch": 0.297441998810232,
|
| 3388 |
+
"grad_norm": 11.668280601501465,
|
| 3389 |
+
"learning_rate": 5.695740637354591e-07,
|
| 3390 |
+
"loss": 1.2407,
|
| 3391 |
+
"step": 4500
|
| 3392 |
+
},
|
| 3393 |
+
{
|
| 3394 |
+
"epoch": 0.297441998810232,
|
| 3395 |
+
"eval_loss": 1.2155283689498901,
|
| 3396 |
+
"eval_runtime": 48.0067,
|
| 3397 |
+
"eval_samples_per_second": 10.436,
|
| 3398 |
+
"eval_steps_per_second": 10.436,
|
| 3399 |
+
"step": 4500
|
| 3400 |
}
|
| 3401 |
],
|
| 3402 |
"logging_steps": 10,
|
|
|
|
| 3416 |
"attributes": {}
|
| 3417 |
}
|
| 3418 |
},
|
| 3419 |
+
"total_flos": 3.104694939554611e+17,
|
| 3420 |
"train_batch_size": 4,
|
| 3421 |
"trial_name": null,
|
| 3422 |
"trial_params": null
|